no code implementations • ECCV 2020 • Hongwei Yong, Jianqiang Huang, Deyu Meng, Xian-Sheng Hua, Lei Zhang
To make a deeper understanding of BN, in this work we prove that BN actually introduces a certain level of noise into the sample mean and variance during the training process, while the noise level depends only on the batch size.
no code implementations • 16 Apr 2024 • Haodong Wen, Bodong Du, Ruixun Liu, Deyu Meng, Xiangyong Cao
Subsequently, PNCA is used to analyze the mainstream polynomial filters, and a novel simple basis that decouples the positive and negative activation and fully utilizes graph structure information is designed.
1 code implementation • 18 Mar 2024 • Datao Tang, Xiangyong Cao, Xingsong Hou, Zhongyuan Jiang, Deyu Meng
The emergence of diffusion models has revolutionized the field of image generation, providing new methods for creating high-quality, high-resolution images across various applications.
no code implementations • 15 Mar 2024 • Zhiqiang Pang, Hong Wang, Qi Xie, Deyu Meng, Zongben Xu
Our unpaired generation experiments demonstrate that the rain generated by the proposed rain generator is not only of higher quality, but also more effective for deraining and downstream tasks compared to current state-of-the-art rain generation methods.
no code implementations • 5 Mar 2024 • Chenqiang Gao, Chuandong Liu, Jun Shu, Fangcen Liu, Jiang Liu, Luyu Yang, Xinbo Gao, Deyu Meng
Current state-of-the-art (SOTA) 3D object detection methods often require a large amount of 3D bounding box annotations for training.
no code implementations • 1 Mar 2024 • Junjie Guo, Chenqiang Gao, Fangcen Liu, Deyu Meng, Xinbo Gao
To effectively mine the complementary information and adapt to misalignment situations, we propose a Multispectral Deformable Cross-attention module to adaptively sample and aggregate multi-semantic level features of infrared and visible images for each object.
1 code implementation • 24 Feb 2024 • Li Pang, Xiangyu Rui, Long Cui, Hongzhong Wang, Deyu Meng, Xiangyong Cao
Specifically, the reduced image, which has a low spectral dimension, lies in the image field and can be inferred from our improved diffusion model where a new guidance function with total variation (TV) prior is designed to ensure that the reduced image can be well sampled.
no code implementations • 23 Feb 2024 • Hui Lin, Zhiheng Ma, Rongrong Ji, YaoWei Wang, Zhou Su, Xiaopeng Hong, Deyu Meng
This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled.
no code implementations • 16 Feb 2024 • Jun-Jie Zhang, Deyu Meng
Neural networks demonstrate inherent vulnerability to small, non-random perturbations, emerging as adversarial attacks.
no code implementations • 1 Feb 2024 • Fangcen Liu, Chenqiang Gao, Yaming Zhang, Junjie Guo, Jinhao Wang, Deyu Meng
Finally, based on the fact that infrared images do not have a lot of details and texture information, we design an infrared decoder module, which further improves the performance of downstream tasks.
1 code implementation • 8 Jan 2024 • Hui Lin, Zhiheng Ma, Xiaopeng Hong, Qinnan Shangguan, Deyu Meng
The graph is building upon the dissimilarities between patches, modulating the attention in an anti-similarity fashion.
no code implementations • 1 Jan 2024 • YiSi Luo, XiLe Zhao, Deyu Meng
Extensive multi-dimensional data processing experiments on-meshgrid (e. g., image inpainting and image denoising) and off-meshgrid (e. g., climate data prediction and point cloud recovery) validate the versatility, effectiveness, and efficiency of our CRNL as compared with state-of-the-art methods.
1 code implementation • 25 Dec 2023 • Jiahong Fu, Qi Xie, Deyu Meng, Zongben Xu
In current deep unfolding methods, such a proximal network is generally designed as a CNN architecture, whose necessity has been proven by a recent theory.
no code implementations • 14 Dec 2023 • Xinyi Liu, Qian Zhao, Jie Liang, Hui Zeng, Deyu Meng, Lei Zhang
Currently, joint image filtering-inspired deep learning-based methods represent the state-of-the-art for GIR tasks.
2 code implementations • 2 Dec 2023 • Kaiyu Li, Xiangyong Cao, Deyu Meng
Change detection (CD) is a critical task to observe and analyze dynamic processes of land cover.
Building change detection for remote sensing images Change Detection +1
no code implementations • 4 Oct 2023 • Kaidong Wang, Yao Wang, Xiuwu Liao, Shaojie Tang, Can Yang, Deyu Meng
For the model, we establish a rigorous mathematical representation of the dynamic graph, based on which we derive a new tensor-oriented graph smoothness regularization.
no code implementations • 27 Sep 2023 • Zihong Sun, Qi Xie, Deyu Meng
To embed more equivariance into CNNs and achieve the accuracy requirement for retinal vessel segmentation, we construct a novel convolution operator (FRS-Conv), which is Fourier parameterized and equivariant to rotation and scaling.
no code implementations • 4 Sep 2023 • Zilong Zhang, Zhibin Zhao, Deyu Meng, Xingwu Zhang, Xuefeng Chen
We generalize the center-based method to unknown classes and optimize this objective based on the prior existing in the pre-trained network, i. e., pre-trained features that belong to the same class are adjacent.
no code implementations • 4 Sep 2023 • Yuanshuo Cheng, Mingwen Shao, Yecong Wan, Yuanjian Qiao, WangMeng Zuo, Deyu Meng
To empower the framework for eliminating diverse degradations, we devise a Sequence-wise Adaptive Degradation Estimator (SADE) to estimate degradation features for the input corrupted video.
1 code implementation • 31 Aug 2023 • Shuang Xu, Yifan Wang, Zixiang Zhao, Jiangjun Peng, Xiangyong Cao, Deyu Meng, Yulun Zhang, Radu Timofte, Luc van Gool
NGR is applicable to various image types and different image processing tasks, functioning in a zero-shot learning fashion, making it a versatile and plug-and-play regularizer.
1 code implementation • ICCV 2023 • Quanziang Wang, Renzhen Wang, Yichen Wu, Xixi Jia, Deyu Meng
Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams.
no code implementations • 16 Jun 2023 • Yuntao Shou, Xiangyong Cao, Deyu Meng, Bo Dong, Qinghua Zheng
By setting a matching weight and calculating attention scores between modal features row by row, LMAM contains fewer parameters than the self-attention method.
1 code implementation • 18 May 2023 • Xiangyu Rui, Xiangyong Cao, Li Pang, Zeyu Zhu, Zongsheng Yue, Deyu Meng
To address these issues, in this work, we propose a low-rank diffusion model for hyperspectral pansharpening by simultaneously leveraging the power of the pre-trained deep diffusion model and better generalization ability of Bayesian methods.
1 code implementation • 13 May 2023 • Jun Shu, Xiang Yuan, Deyu Meng, Zongben Xu
Besides, meta-data-driven meta-loss objective combined with DAC-MR is capable of achieving better meta-level generalization.
no code implementations • ICCV 2023 • Gang Yang, Xiangyong Cao, Wenzhe Xiao, Man Zhou, Aiping Liu, Xun Chen, Deyu Meng
The experimental results verify that the proposed PanFlowNet can generate various HRMS images given an LRMS image and a PAN image.
2 code implementations • 12 May 2023 • Ye Deng, Siqi Hui, Sanping Zhou, Deyu Meng, Jinjun Wang
And based on this attention, a network called $T$-former is designed for image inpainting.
1 code implementation • CVPR 2023 • Chuandong Liu, Chenqiang Gao, Fangcen Liu, Pengcheng Li, Deyu Meng, Xinbo Gao
State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations.
no code implementations • 29 Mar 2023 • Man Zhou, Naishan Zheng, Jie Huang, Xiangyu Rui, Chunle Guo, Deyu Meng, Chongyi Li, Jinwei Gu
In this paper, orthogonal to the existing data and model studies, we instead resort our efforts to investigate the potential of loss function in a new perspective and present our belief ``Random Weights Networks can Be Acted as Loss Prior Constraint for Image Restoration''.
1 code implementation • CVPR 2023 • Zhemin Li, Hongxia Wang, Deyu Meng
The smoothness of the Laplacian matrix is further integrated by parameterizing DE with a tiny INR.
2 code implementations • ICCV 2023 • Zixiang Zhao, Haowen Bai, Yuanzhi Zhu, Jiangshe Zhang, Shuang Xu, Yulun Zhang, Kai Zhang, Deyu Meng, Radu Timofte, Luc van Gool
To leverage strong generative priors and address challenges such as unstable training and lack of interpretability for GAN-based generative methods, we propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM).
1 code implementation • CVPR 2023 • Zeyu Zhu, Xiangyong Cao, Man Zhou, Junhao Huang, Deyu Meng
Pansharpening is an essential preprocessing step for remote sensing image processing.
1 code implementation • 28 Feb 2023 • Minghao Zhou, Hong Wang, Qian Zhao, Yuexiang Li, Yawen Huang, Deyu Meng, Yefeng Zheng
Against this issue, in this paper, we propose to formulate the IS task as a Gaussian process (GP)-based pixel-wise binary classification model on each image.
1 code implementation • 4 Feb 2023 • Hailin Wang, Jiangjun Peng, Wenjin Qin, Jianjun Wang, Deyu Meng
Recent research have made significant progress by adopting two insightful tensor priors, i. e., global low-rankness (L) and local smoothness (S) across different tensor modes, which are always encoded as a sum of two separate regularization terms into the recovery models.
no code implementations • 18 Jan 2023 • Kehui Ding, Jun Shu, Deyu Meng, Zongben Xu
To achieve setting such instance-dependent hyperparameters for robust loss, we propose a meta-learning method capable of adaptively learning a hyperparameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster).
1 code implementation • 15 Jan 2023 • Jinhui Hou, Zhiyu Zhu, Junhui Hou, Hui Liu, Huanqiang Zeng, Deyu Meng
In this paper, we study the problem of efficiently and effectively embedding the high-dimensional spatio-spectral information of hyperspectral (HS) images, guided by feature diversity.
1 code implementation • CVPR 2023 • Minghao Zhou, Hong Wang, Qian Zhao, Yuexiang Li, Yawen Huang, Deyu Meng, Yefeng Zheng
Against this issue, in this paper, we propose to formulate the IS task as a Gaussian process (GP)-based pixel-wise binary classification model on each image.
no code implementations • 1 Jan 2023 • Chenyu Xue, Fan Wang, Yuanzhuo Zhu, Hui Li, Deyu Meng, Dinggang Shen, Chunfeng Lian
Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and (even more importantly) explainable predictions.
no code implementations • ICCV 2023 • Yongheng Sun, Fan Wang, Jun Shu, Haifeng Wang, Li Wang, Deyu Meng, Chunfeng Lian
However, segmentation on longitudinal data is challenging due to dynamic brain changes across the lifespan.
no code implementations • 27 Dec 2022 • Zitai Xu, YiSi Luo, Bangyu Wu, Deyu Meng
In this work, we propose a self-supervised method that combines the capacities of deep denoiser and the generalization abilities of hand-crafted regularization for seismic data random noise attenuation.
1 code implementation • 26 Dec 2022 • Hong Wang, Qi Xie, Yuexiang Li, Yawen Huang, Deyu Meng, Yefeng Zheng
During X-ray computed tomography (CT) scanning, metallic implants carrying with patients often lead to adverse artifacts in the captured CT images and then impair the clinical treatment.
no code implementations • 9 Dec 2022 • Xiangyu Rui, Xiangyong Cao, Jun Shu, Qian Zhao, Deyu Meng
Extensive experiments verify that the proposed HWnet can help improve the generalization ability of a weighted model to adapt to more complex noise, and can also strengthen the weighted model by transferring the knowledge from another weighted model.
no code implementations • 1 Dec 2022 • YiSi Luo, XiLe Zhao, Zhemin Li, Michael K. Ng, Deyu Meng
To break this barrier, we propose a low-rank tensor function representation (LRTFR), which can continuously represent data beyond meshgrid with infinite resolution.
no code implementations • 3 Nov 2022 • Jiangjun Peng, Hailin Wang, Xiangyong Cao, Xinlin Liu, Xiangyu Rui, Deyu Meng
The model-based methods have good generalization ability, while the runtime cannot meet the fast processing requirements of the practical situations due to the large size of an HSI data $ \mathbf{X} \in \mathbb{R}^{MN\times B}$.
1 code implementation • 11 Oct 2022 • Man Zhou, Hu Yu, Jie Huang, Feng Zhao, Jinwei Gu, Chen Change Loy, Deyu Meng, Chongyi Li
Existing convolutional neural networks widely adopt spatial down-/up-sampling for multi-scale modeling.
1 code implementation • 21 Sep 2022 • Jiahong Fu, Hong Wang, Qi Xie, Qian Zhao, Deyu Meng, Zongben Xu
Although current deep learning-based methods have gained promising performance in the blind single image super-resolution (SISR) task, most of them mainly focus on heuristically constructing diverse network architectures and put less emphasis on the explicit embedding of the physical generation mechanism between blur kernels and high-resolution (HR) images.
1 code implementation • 28 Jul 2022 • Renzhen Wang, Xixi Jia, Quanziang Wang, Yichen Wu, Deyu Meng
The core idea is to automatically assimilate the training bias caused by class imbalance via the bias adaptive classifier, which is composed of a novel bias attractor and the original linear classifier.
1 code implementation • 16 May 2022 • Hong Wang, Yuexiang Li, Deyu Meng, Yefeng Zheng
By unfolding every iterative substep of the proposed algorithm into a network module, we explicitly embed the prior structure into a deep network, \emph{i. e.,} a clear interpretability for the MAR task.
1 code implementation • 7 May 2022 • Danfeng Hong, Jing Yao, Deyu Meng, Naoto Yokoya, Jocelyn Chanussot
Enormous efforts have been recently made to super-resolve hyperspectral (HS) images with the aid of high spatial resolution multispectral (MS) images.
Hyperspectral Image Super-Resolution Image Super-Resolution +1
no code implementations • 3 May 2022 • Jun-Jie Zhang, Dong-Xiao Zhang, Jian-Nan Chen, Long-Gang Pang, Deyu Meng
Despite the successes in many fields, it is found that neural networks are difficult to be both accurate and robust, i. e., high accuracy networks are often vulnerable.
1 code implementation • 19 Apr 2022 • Yue Zhao, Lingming Zhang, Yang Liu, Deyu Meng, Zhiming Cui, Chenqiang Gao, Xinbo Gao, Chunfeng Lian, Dinggang Shen
The state-of-the-art deep learning-based methods often simply concatenate the raw geometric attributes (i. e., coordinates and normal vectors) of mesh cells to train a single-stream network for automatic intra-oral scanner image segmentation.
no code implementations • 16 Feb 2022 • Minghao Zhou, Quanziang Wang, Jun Shu, Qian Zhao, Deyu Meng
Extensive researches have applied deep neural networks (DNNs) in class incremental learning (Class-IL).
no code implementations • 12 Feb 2022 • Xinyi Liu, Qi Xie, Qian Zhao, Hong Wang, Deyu Meng
Besides, to avoid manually parameter tuning, we also propose a self-supervised fine-tuning strategy, which can always guarantee a promising performance.
1 code implementation • 11 Feb 2022 • Jun Shu, Xiang Yuan, Deyu Meng, Zongben Xu
Specifically, by seeing each training class as a separate learning task, our method aims to extract an explicit weighting function with sample loss and task/class feature as input, and sample weight as output, expecting to impose adaptively varying weighting schemes to different sample classes based on their own intrinsic bias characteristics.
Ranked #3 on Image Classification on WebVision-1000
no code implementations • 29 Jan 2022 • Jiangjun Peng, Yao Wang, Hongying Zhang, Jianjun Wang, Deyu Meng
It is known that the decomposition in low-rank and sparse matrices (\textbf{L+S} for short) can be achieved by several Robust PCA techniques.
no code implementations • CVPR 2022 • Chuandong Liu, Chenqiang Gao, Fangcen Liu, Jiang Liu, Deyu Meng, Xinbo Gao
In the meantime, we design a reliable background mining module and a point cloud filling data augmentation strategy to generate the confident data for iteratively learning with reliable supervision.
no code implementations • CVPR 2022 • YiSi Luo, Xi-Le Zhao, Deyu Meng, Tai-Xiang Jiang
Inverse problems in multi-dimensional imaging, e. g., completion, denoising, and compressive sensing, are challenging owing to the big volume of the data and the inherent ill-posedness.
no code implementations • 31 Dec 2021 • Quanziang Wang, Renzhen Wang, Yuexiang Li, Dong Wei, Kai Ma, Yefeng Zheng, Deyu Meng
Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data.
no code implementations • 29 Dec 2021 • Shuyin Xia, Xinyu Bai, Guoyin Wang, Deyu Meng, Xinbo Gao, Zizhong Chen, Elisabeth Giem
This paper present a strong data mining method based on rough set, which can realize feature selection, classification and knowledge representation at the same time.
1 code implementation • 23 Dec 2021 • Hong Wang, Yuexiang Li, Haimiao Zhang, Deyu Meng, Yefeng Zheng
To alleviate these issues, in the paper, we construct a novel deep unfolding dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded.
1 code implementation • 4 Dec 2021 • Renzhen Wang, De Cai, Kaiwen Xiao, Xixi Jia, Xiao Han, Deyu Meng
Existing methods commonly address hierarchical classification by decoupling it into a series of multi-class classification tasks.
no code implementations • 29 Sep 2021 • Fangcen Liu, Chenqiang Gao, Fang Chen, Deyu Meng, WangMeng Zuo, Xinbo Gao
We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range.
1 code implementation • 11 Sep 2021 • Hong Wang, Yuexiang Li, Haimiao Zhang, Jiawei Chen, Kai Ma, Deyu Meng, Yefeng Zheng
For the task of metal artifact reduction (MAR), although deep learning (DL)-based methods have achieved promising performances, most of them suffer from two problems: 1) the CT imaging geometry constraint is not fully embedded into the network during training, leaving room for further performance improvement; 2) the model interpretability is lack of sufficient consideration.
1 code implementation • 21 Aug 2021 • Huai Chen, Renzhen Wang, Xiuying Wang, Jieyu Li, Qu Fang, Hui Li, Jianhao Bai, Qing Peng, Deyu Meng, Lisheng Wang
To address this challenge, in this paper, we propose a general unsupervised representation learning framework, named local discrimination (LD), to learn local discriminative features for medical images by closely embedding semantically similar pixels and identifying regions of similar structures across different images.
1 code implementation • 13 Aug 2021 • Fang Chen, Chenqiang Gao, Fangcen Liu, Yue Zhao, Yuxi Zhou, Deyu Meng, WangMeng Zuo
A local patch network (LPNet) with global attention is proposed in this paper to detect small targets by jointly considering the global and local properties of infrared small target images.
1 code implementation • 30 Jul 2021 • Qi Xie, Qian Zhao, Zongben Xu, Deyu Meng
It has been shown that equivariant convolution is very helpful for many types of computer vision tasks.
1 code implementation • 14 Jul 2021 • Hong Wang, Qi Xie, Qian Zhao, Yuexiang Li, Yong Liang, Yefeng Zheng, Deyu Meng
To handle such an ill-posed single image deraining task, in this paper, we specifically build a novel deep architecture, called rain convolutional dictionary network (RCDNet), which embeds the intrinsic priors of rain streaks and has clear interpretability.
1 code implementation • 6 Jul 2021 • Jun Shu, Deyu Meng, Zongben Xu
Meta learning has attracted much attention recently in machine learning community.
1 code implementation • CVPR 2022 • Zongsheng Yue, Qian Zhao, Jianwen Xie, Lei Zhang, Deyu Meng, Kwan-Yee K. Wong
To address the above issues, this paper proposes a model-based blind SISR method under the probabilistic framework, which elaborately models image degradation from the perspectives of noise and blur kernel.
no code implementations • 27 Jun 2021 • Quanziang Wang, Renzhen Wang, Yuexiang Li, Kai Ma, Yefeng Zheng, Deyu Meng
Location information is proven to benefit the deep learning models on capturing the manifold structure of target objects, and accordingly boosts the accuracy of medical image segmentation.
1 code implementation • 23 Jun 2021 • Zeyu Gao, Bangyang Hong, Xianli Zhang, Yang Li, Chang Jia, Jialun Wu, Chunbao Wang, Deyu Meng, Chen Li
Histological subtype of papillary (p) renal cell carcinoma (RCC), type 1 vs. type 2, is an essential prognostic factor.
1 code implementation • 20 Jun 2021 • Zeyu Gao, Jiangbo Shi, Xianli Zhang, Yang Li, Haichuan Zhang, Jialun Wu, Chunbao Wang, Deyu Meng, Chen Li
In this paper, we propose a Composite High-Resolution Network for ccRCC nuclei grading.
no code implementations • CVPR 2021 • Lingming Zhang, Yue Zhao, Deyu Meng, Zhiming Cui, Chenqiang Gao, Xinbo Gao, Chunfeng Lian, Dinggang Shen
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
no code implementations • CVPR 2021 • Xiangyu Rui, Xiangyong Cao, Qi Xie, Zongsheng Yue, Qian Zhao, Deyu Meng
A general approach for handling hyperspectral image (HSI) denoising issue is to impose weights on different HSI pixels to suppress negative influence brought by noisy elements.
1 code implementation • CVPR 2021 • Haiquan Qiu, Yao Wang, Deyu Meng
Specifically, we propose an optimization objective to utilize these two priors.
no code implementations • 5 Jun 2021 • Hui Wang, Zongsheng Yue, Qian Zhao, Deyu Meng
Under this framework, the posterior of the latent clean image and blur kernel can be jointly estimated in an amortized inference fashion with DNNs, and the involved inference DNNs can be trained by fully considering the physical blur model, together with the supervision of data driven priors for the clean image and blur kernel, which is naturally led to by the evidence lower bound objective.
3 code implementations • 30 May 2021 • Hu Zhang, Keke Zu, Jian Lu, Yuru Zou, Deyu Meng
Recently, it has been demonstrated that the performance of a deep convolutional neural network can be effectively improved by embedding an attention module into it.
1 code implementation • CVPR 2021 • Zongsheng Yue, Jianwen Xie, Qian Zhao, Deyu Meng
Firstly, most of them do not sufficiently model the characteristics of rain layers of rainy videos.
1 code implementation • 27 Jan 2021 • Risheng Liu, Jiaxin Gao, Jin Zhang, Deyu Meng, Zhouchen Lin
Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community.
no code implementations • 1 Jan 2021 • Jinwei Zhao, Qizhou Wang, Wanli Qiu, Guo Xie, Wei Wang, Xinhong Hei, Deyu Meng
However, it is hard for the interpretable models to approximate the discrimination part because of the tradeoff problem between interpretability performance and generalization performance of the discrimination part.
no code implementations • 26 Dec 2020 • Lingming Zhang, Yue Zhao, Deyu Meng, Zhiming Cui, Chenqiang Gao, Xinbo Gao, Chunfeng Lian, Dinggang Shen
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
1 code implementation • 17 Dec 2020 • Huai Chen, Jieyu Li, Renzhen Wang, YiJie Huang, Fanrui Meng, Deyu Meng, Qing Peng, Lisheng Wang
However, the commonly applied supervised representation learning methods require a large amount of annotated data, and unsupervised discriminative representation learning distinguishes different images by learning a global feature, both of which are not suitable for localized medical image analysis tasks.
no code implementations • 2 Sep 2020 • Ziyi Yang, Jun Shu, Yong Liang, Deyu Meng, Zongben Xu
Current machine learning has made great progress on computer vision and many other fields attributed to the large amount of high-quality training samples, while it does not work very well on genomic data analysis, since they are notoriously known as small data.
2 code implementations • 25 Aug 2020 • Zongsheng Yue, Hongwei Yong, Qian Zhao, Lei Zhang, Deyu Meng, Kwan-Yen K. Wong
In this proposed model, a pixel-wise non-i. i. d.
no code implementations • 8 Aug 2020 • Renzhen Wang, Kaiqin Hu, Yanwen Zhu, Jun Shu, Qian Zhao, Deyu Meng
We further design a modulator network to guide the generation of the modulation parameters, and such a meta-learner can be readily adapted to train the classification network on other long-tailed datasets.
1 code implementation • CVPR 2021 • Hong Wang, Zongsheng Yue, Qi Xie, Qian Zhao, Yefeng Zheng, Deyu Meng
For the single image rain removal (SIRR) task, the performance of deep learning (DL)-based methods is mainly affected by the designed deraining models and training datasets.
1 code implementation • 3 Aug 2020 • Yichen Wu, Jun Shu, Qi Xie, Qian Zhao, Deyu Meng
By viewing the label correction procedure as a meta-process and using a meta-learner to automatically correct labels, we could adaptively obtain rectified soft labels iteratively according to current training problems without manually preset hyper-parameters.
no code implementations • 29 Jul 2020 • Jun Shu, Yanwen Zhu, Qian Zhao, Zongben Xu, Deyu Meng
Meanwhile, it always needs to search proper LR schedules from scratch for new tasks, which, however, are often largely different with task variations, like data modalities, network architectures, or training data capacities.
2 code implementations • ECCV 2020 • Zongsheng Yue, Qian Zhao, Lei Zhang, Deyu Meng
Specifically, we approximate the joint distribution with two different factorized forms, which can be formulated as a denoiser mapping the noisy image to the clean one and a generator mapping the clean image to the noisy one.
Ranked #2 on Noise Estimation on SIDD
1 code implementation • ECCV 2020 • Jing Yao, Danfeng Hong, Jocelyn Chanussot, Deyu Meng, Xiaoxiang Zhu, Zongben Xu
The recent advancement of deep learning techniques has made great progress on hyperspectral image super-resolution (HSI-SR).
no code implementations • 10 Jun 2020 • Jun Shu, Qian Zhao, Zongben Xu, Deyu Meng
To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels.
no code implementations • 19 May 2020 • Hong Wang, Yichen Wu, Qi Xie, Qian Zhao, Yong Liang, Deyu Meng
Such a structural residual setting guarantees the rain layer extracted by the network finely comply with the prior knowledge of general rain streaks, and thus regulates sound rain shapes capable of being well extracted from rainy images in both training and predicting stages.
1 code implementation • CVPR 2020 • Hong Wang, Qi Xie, Qian Zhao, Deyu Meng
Specifically, based on the convolutional dictionary learning mechanism for representing rain, we propose a novel single image deraining model and utilize the proximal gradient descent technique to design an iterative algorithm only containing simple operators for solving the model.
no code implementations • 2 May 2020 • Shuyin Xia, Daowan Peng, Deyu Meng, Changqing Zhang, Guoyin Wang, Zizhong Chen, Wei Wei
The assigned cluster of the points in the stable area is not changed in the current iteration while the points in the annulus area will be adjusted within a few neighbor clusters in the current iteration.
no code implementations • CVPR 2020 • Shuxin Wang, Shilei Cao, Dong Wei, Renzhen Wang, Kai Ma, Liansheng Wang, Deyu Meng, Yefeng Zheng
We introduce a one-shot segmentation method to alleviate the burden of manual annotation for medical images.
no code implementations • 16 Feb 2020 • Jun Shu, Qian Zhao, Keyu Chen, Zongben Xu, Deyu Meng
Four kinds of SOTA robust loss functions are attempted to be integrated into our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its accuracy and generalization performance, as compared with conventional hyperparameter tuning strategy, even with carefully tuned hyperparameters.
1 code implementation • 18 Sep 2019 • Hong Wang, Yichen Wu, Minghan Li, Qian Zhao, Deyu Meng
The investigations on rain removal from video or a single image has thus been attracting much research attention in the field of computer vision and pattern recognition, and various methods have been proposed against this task in the recent years.
1 code implementation • 13 Sep 2019 • Minghan Li, Xiangyong Cao, Qian Zhao, Lei Zhang, Chenqiang Gao, Deyu Meng
Furthermore, a transformation operator imposed on the background scenes is further embedded into the proposed model, which finely conveys the dynamic background transformations, such as rotations, scalings and distortions, inevitably existed in a real video sequence.
2 code implementations • NeurIPS 2019 • Zongsheng Yue, Hongwei Yong, Qian Zhao, Lei Zhang, Deyu Meng
On one hand, as other data-driven deep learning methods, our method, namely variational denoising network (VDN), can perform denoising efficiently due to its explicit form of posterior expression.
Ranked #10 on Image Denoising on DND
3 code implementations • NeurIPS 2019 • Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, Deyu Meng
Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance.
Ranked #24 on Image Classification on Clothing1M (using extra training data)
4 code implementations • CVPR 2019 • Dongwei Ren, WangMeng Zuo, QinGhua Hu, Pengfei Zhu, Deyu Meng
To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions.
Ranked #1 on Single Image Deraining on Rain1400
no code implementations • CVPR 2019 • Qi Xie, Minghao Zhou, Qian Zhao, Deyu Meng, WangMeng Zuo, Zongben Xu
In this paper, we propose a model-based deep learning approach for merging an HrMS and LrHS images to generate a high-resolution hyperspectral (HrHS) image.
no code implementations • 7 Nov 2018 • Hongwei Yong, Deyu Meng, Jinxing Li, WangMeng Zuo, Lei Zhang
Different from single view case, MSL should take both common and specific knowledge among different views into consideration.
no code implementations • 18 Sep 2018 • Jiangjun Peng, Qi Xie, Qian Zhao, Yao Wang, Deyu Meng, Yee Leung
The 3-D total variation (3DTV) is a powerful regularization term, which encodes the local smoothness prior structure underlying a hyper-spectral image (HSI), for general HSI processing tasks.
1 code implementation • 6 Sep 2018 • Shiqi Liu, Jingxin Liu, Qian Zhao, Xiangyong Cao, Huibin Li, Hongy-ing Meng, Sheng Liu, Deyu Meng
In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks.
no code implementations • 14 Aug 2018 • Jun Shu, Zongben Xu, Deyu Meng
This category mainly focuses on learning with insufficient samples, and can also be called small data learning in some literatures.
no code implementations • 8 Aug 2018 • Mingrui Geng, Yun Deng, Qian Zhao, Qi Xie, Dong Zeng, WangMeng Zuo, Deyu Meng
To address this issue, we propose an unsupervised DL method for LdCT enhancement that incorporates unlabeled LdCT sinograms directly into the network training.
1 code implementation • CVPR 2019 • Wei Wei, Deyu Meng, Qian Zhao, Zongben Xu, Ying Wu
However, previous deep learning methods need to pre-collect a large set of image pairs with/without synthesized rain for training, which tends to make the neural network be biased toward learning the specific patterns of the synthesized rain, while be less able to generalize to real test samples whose rain types differ from those in the training data.
Ranked #8 on Single Image Deraining on Test100
3 code implementations • 26 Jul 2018 • Jun Xu, Mengyang Yu, Ling Shao, WangMeng Zuo, Deyu Meng, Lei Zhang, David Zhang
However, the negative entries in the coefficient matrix are forced to be positive when constructing the affinity matrix via exponentiation, absolute symmetrization, or squaring operations.
no code implementations • 4 Jul 2018 • Sanping Zhou, Jinjun Wang, Deyu Meng, Yudong Liang, Yihong Gong, Nanning Zheng
Specifically, a novel foreground attentive subnetwork is designed to drive the network's attention, in which a decoder network is used to reconstruct the binary mask by using a novel local regression loss function, and an encoder network is regularized by the decoder network to focus its attention on the foreground persons.
no code implementations • CVPR 2018 • Minghan Li, Qi Xie, Qian Zhao, Wei Wei, Shuhang Gu, Jing Tao, Deyu Meng
Based on such understanding, we specifically formulate both characteristics into a multiscale convolutional sparse coding (MS-CSC) model for the video rain streak removal task.
no code implementations • 21 May 2018 • Shiqi Liu, Zilu Ma, Deyu Meng
By simulating the easy-to-hard learning manners of humans/animals, the learning regimes called curriculum learning~(CL) and self-paced learning~(SPL) have been recently investigated and invoked broad interests.
no code implementations • ECCV 2018 • Lan Wang, Chenqiang Gao, Luyu Yang, Yue Zhao, WangMeng Zuo, Deyu Meng
As a result, using partial data channels to build a full representation of multi-modalities is clearly desired.
no code implementations • ICLR 2018 • Shiqi Liu, Qian Zhao, Xiangyong Cao, Deyu Meng, Zilu Ma, Tao Yu
This paper tries to preliminarily address VAE's intrinsic dimension, real factor, disentanglement and indicator issues theoretically in the idealistic situation and implementation issue practically through noise modeling perspective in the realistic case.
1 code implementation • CVPR 2018 • Jiang Liu, Chenqiang Gao, Deyu Meng, Alexander G. Hauptmann
DecideNet starts with estimating the crowd density by generating detection and regression based density maps separately.
Ranked #10 on Crowd Counting on WorldExpo’10
no code implementations • 7 Oct 2017 • Sanping Zhou, Jinjun Wang, Deyu Meng, Xiaomeng Xin, Yubing Li, Yihong Gong, Nanning Zheng
In this paper, we propose a novel deep self-paced learning (DSPL) algorithm to alleviate this problem, in which we apply a self-paced constraint and symmetric regularization to help the relative distance metric training the deep neural network, so as to learn the stable and discriminative features for person Re-ID.
no code implementations • ICCV 2017 • Shuhang Gu, Deyu Meng, WangMeng Zuo, Lei Zhang
To exploit the complementary representation mechanisms of ASR and SSR, we integrate the two models and propose a joint convolutional analysis and synthesis (JCAS) sparse representation model.
no code implementations • ICCV 2017 • Qiong Luo, Zhi Han, Xi'ai Chen, Yao Wang, Deyu Meng, Dong Liang, Yandong Tang
In this paper, we propose a tensor RPCA model based on CP decomposition and model data noise by Mixture of Gaussians (MoG).
no code implementations • ICCV 2017 • Wei Wei, Lixuan Yi, Qi Xie, Qian Zhao, Deyu Meng, Zongben Xu
Videos taken in the wild sometimes contain unexpected rain streaks, which brings difficulty in subsequent video processing tasks.
no code implementations • ICML 2017 • Fan Ma, Deyu Meng, Qi Xie, Zina Li, Xuanyi Dong
During co-training process, labels of unlabeled instances in the training pool are very likely to be false especially in the initial training rounds, while the standard co-training algorithm utilizes a “draw without replacement” manner and does not remove these false labeled instances from training.
no code implementations • 8 Jul 2017 • Yao Wang, Jiangjun Peng, Qian Zhao, Deyu Meng, Yee Leung, Xi-Le Zhao
In this paper, we present a novel tensor-based HSI restoration approach by fully identifying the intrinsic structures of the clean HSI part and the mixed noise part respectively.
no code implementations • CVPR 2017 • Dingwen Zhang, Le Yang, Deyu Meng, Dong Xu, Junwei Han
Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform category-specific video object segmentation by only using video-level tags.
1 code implementation • 26 Jun 2017 • Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, Deyu Meng
Experiments on PASCAL VOC'07, MS COCO'14, and ILSVRC'13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.
Ranked #1 on Weakly Supervised Object Detection on MS COCO
no code implementations • 20 Jun 2017 • Kaidong Wang, Yao Wang, Qian Zhao, Deyu Meng, Zongben Xu
Specifically, the underlying loss being minimized by the traditional AdaBoost is the exponential loss, which is proved to be very sensitive to random noise/outliers.
no code implementations • 28 May 2017 • Hongwei Yong, Deyu Meng, WangMeng Zuo, Lei Zhang
We propose an effective online background subtraction method, which can be robustly applied to practical videos that have variations in both foreground and background.
no code implementations • 18 May 2017 • Xi'ai Chen, Zhi Han, Yao Wang, Qian Zhao, Deyu Meng, Lin Lin, Yandong Tang
We provide two versions of the algorithm with different tensor factorization operations, i. e., CP factorization and Tucker factorization.
1 code implementation • 1 May 2017 • Xiangyong Cao, Feng Zhou, Lin Xu, Deyu Meng, Zongben Xu, John Paisley
This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework.
Ranked #13 on Hyperspectral Image Classification on Indian Pines (Overall Accuracy metric, using extra training data)
no code implementations • 29 Mar 2017 • Zilu Ma, Shiqi Liu, Deyu Meng
Recently, it has been proved that the SPL regime has a close relationship to a implicit self-paced objective function.
no code implementations • 3 Mar 2017 • Dingwen Zhang, Deyu Meng, Long Zhao, Junwei Han
Weakly-supervised object detection (WOD) is a challenging problems in computer vision.
Ranked #34 on Weakly Supervised Object Detection on PASCAL VOC 2007
no code implementations • 1 Feb 2017 • Yang Chen, Xiangyong Cao, Qian Zhao, Deyu Meng, Zongben Xu
In real scenarios, however, the noise existed in a natural HSI is always with much more complicated non-i. i. d.
no code implementations • 13 Jan 2017 • Liang Lin, Keze Wang, Deyu Meng, WangMeng Zuo, Lei Zhang
By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert re-certification.
20 code implementations • 13 Aug 2016 • Kai Zhang, WangMeng Zuo, Yunjin Chen, Deyu Meng, Lei Zhang
Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance.
1 code implementation • 16 Jul 2016 • Junwei Liang, Lu Jiang, Deyu Meng, Alexander Hauptmann
Learning video concept detectors automatically from the big but noisy web data with no additional manual annotations is a novel but challenging area in the multimedia and the machine learning community.
no code implementations • 17 Jun 2016 • Shoou-I Yu, Yi Yang, Zhongwen Xu, Shicheng Xu, Deyu Meng, Zexi Mao, Zhigang Ma, Ming Lin, Xuanchong Li, Huan Li, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann, Chuang Gan, Xingzhong Du, Xiaojun Chang
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.
no code implementations • CVPR 2016 • Qi Xie, Qian Zhao, Deyu Meng, Zongben Xu, Shuhang Gu, WangMeng Zuo, Lei Zhang
Multispectral images (MSI) can help deliver more faithful representation for real scenes than the traditional image system, and enhance the performance of many computer vision tasks.
no code implementations • CVPR 2016 • Xi'ai Chen, Zhi Han, Yao Wang, Qian Zhao, Deyu Meng, Yandong Tang
However, real data are often corrupted by noise with an unknown distribution.
no code implementations • CVPR 2016 • Shoou-I Yu, Deyu Meng, WangMeng Zuo, Alexander Hauptmann
The tracker is formulated as a quadratic optimization problem with L0 norm constraints, which we propose to solve with the solution path algorithm.
no code implementations • 7 Mar 2016 • Lan Wang, Chenqiang Gao, Jiang Liu, Deyu Meng
Detecting complex events in a large video collection crawled from video websites is a challenging task.
no code implementations • ICCV 2015 • Xiangyong Cao, Qian Zhao, Deyu Meng, Yang Chen, Zongben Xu
Many computer vision problems can be posed as learning a low-dimensional subspace from high dimensional data.
no code implementations • ICCV 2015 • Shuhang Gu, WangMeng Zuo, Qi Xie, Deyu Meng, Xiangchu Feng, Lei Zhang
Sparse coding (SC) plays an important role in versatile computer vision applications such as image super-resolution (SR).
no code implementations • ICCV 2015 • Dingwen Zhang, Deyu Meng, Chao Li, Lu Jiang, Qian Zhao, Junwei Han
As an interesting and emerging topic, co-saliency detection aims at simultaneously extracting common salient objects in a group of images.
no code implementations • ICCV 2015 • Qian Zhao, Deyu Meng, Xu Kong, Qi Xie, Wenfei Cao, Yao Wang, Zongben Xu
In this paper, we propose a new sparsity regularizer for measuring the low-rank structure underneath a tensor.
no code implementations • 19 Nov 2015 • Deyu Meng, Qian Zhao, Lu Jiang
Self-paced learning (SPL) is a recently raised methodology designed through simulating the learning principle of humans/animals.
no code implementations • 3 May 2015 • Zhaoxin Li, Kuanquan Wang, WangMeng Zuo, Deyu Meng, Lei Zhang
It is much more promising in suppressing noise while preserving sharp features than conventional isotropic mesh smoothing.
no code implementations • 6 Mar 2015 • Wenfei Cao, Yao Wang, Jian Sun, Deyu Meng, Can Yang, Andrzej Cichocki, Zongben Xu
In this paper, we propose a novel tensor-based robust PCA (TenRPCA) approach for BSCM by decomposing video frames into backgrounds with spatial-temporal correlations and foregrounds with spatio-temporal continuity in a tensor framework.
no code implementations • 2 Feb 2015 • Wangmeng Zuo, Faqiang Wang, David Zhang, Liang Lin, Yuchi Huang, Deyu Meng, Lei Zhang
Distance metric learning aims to learn from the given training data a valid distance metric, with which the similarity between data samples can be more effectively evaluated for classification.
no code implementations • NeurIPS 2014 • Lu Jiang, Deyu Meng, Shoou-I Yu, Zhenzhong Lan, Shiguang Shan, Alexander Hauptmann
Self-paced learning (SPL) is a recently proposed learning regime inspired by the learning process of humans and animals that gradually incorporates easy to more complex samples into training.
no code implementations • 23 Oct 2014 • Ji Zhao, Deyu Meng, Jiayi Ma
Typically, the region search methods project the score of a classifier into an image plane, and then search the region with the maximal score.
no code implementations • CVPR 2014 • Zhiding Yu, Chunjing Xu, Deyu Meng, Zhuo Hui, Fanyi Xiao, Wenbo Liu, Jianzhuang Liu
We propose a very intuitive and simple approximation for the conventional spectral clustering methods.
no code implementations • CVPR 2014 • Yi Peng, Deyu Meng, Zongben Xu, Chenqiang Gao, Yi Yang, Biao Zhang
As compared to the conventional RGB or gray-scale images, multispectral images (MSI) can deliver more faithful representation for real scenes, and enhance the performance of many computer vision tasks.
no code implementations • 23 May 2014 • Qi Xie, Deyu Meng, Shuhang Gu, Lei Zhang, WangMeng Zuo, Xiangchu Feng, Zongben Xu
Nevertheless, so far the global optimal solution of WNNM problem is not completely solved yet due to its non-convexity in general cases.
no code implementations • 12 May 2014 • Ji Zhao, Deyu Meng
Taking advantage of sampling of Fourier transform, FastMMD decreases the time complexity for MMD calculation from $O(N^2 d)$ to $O(L N d)$, where $N$ and $d$ are the size and dimension of the sample set, respectively.
no code implementations • 23 Sep 2013 • Faqiang Wang, WangMeng Zuo, Lei Zhang, Deyu Meng, David Zhang
Learning a distance metric from the given training samples plays a crucial role in many machine learning tasks, and various models and optimization algorithms have been proposed in the past decade.