no code implementations • CCL 2020 • Dinghe Xiao, Nannan Wang, Jiangang Yu, Chunhong Zhang, Jiaqi Wu
So we develop two pipelines of processing methods for semi-structured data and unstructured data respectively.
no code implementations • ECCV 2020 • Jingwei Xin, Nannan Wang, Xinrui Jiang, Jie Li, Heng Huang, Xinbo Gao
Lighter model and faster inference are the focus of current single image super-resolution (SISR) research.
no code implementations • 27 Mar 2024 • Ruoyu Zhao, Qingnan Fan, Fei Kou, Shuai Qin, Hong Gu, Wei Wu, Pengcheng Xu, Mingrui Zhu, Nannan Wang, Xinbo Gao
Two key techniques are introduced into InstructBrush, Attention-based Instruction Optimization and Transformation-oriented Instruction Initialization, to address the limitations of the previous method in terms of inversion effects and instruction generalization.
1 code implementation • 12 Mar 2024 • De Cheng, Yanling Ji, Dong Gong, Yan Li, Nannan Wang, Junwei Han, Dingwen Zhang
It considers the characteristics of the image restoration task with multiple degenerations in continual learning, and the knowledge for different degenerations can be shared and accumulated in the unified network structure.
2 code implementations • 22 Feb 2024 • Yonggang Zhang, Zhiqin Yang, Xinmei Tian, Nannan Wang, Tongliang Liu, Bo Han
Federated semi-supervised learning (FSSL) has emerged as a powerful paradigm for collaboratively training machine learning models using distributed data with label deficiency.
no code implementations • 1 Feb 2024 • Lingfeng He, De Cheng, Nannan Wang, Xinbo Gao
In response, we introduce a Modality-Unified Label Transfer (MULT) module that simultaneously accounts for both homogeneous and heterogeneous fine-grained instance-level structures, yielding high-quality cross-modality label associations.
no code implementations • 29 Jan 2024 • Shiyin Dong, Mingrui Zhu, Kun Cheng, Nannan Wang, Xinbo Gao
Our purpose is to establish a unified visual perception framework, capitalizing on the potential synergies between generative and discriminative models.
no code implementations • 26 Jan 2024 • Nuoyan Zhou, Dawei Zhou, Decheng Liu, Xinbo Gao, Nannan Wang
Deep neural networks are vulnerable to adversarial samples.
1 code implementation • 11 Jan 2024 • Chunlei Peng, Boyu Wang, Decheng Liu, Nannan Wang, Ruimin Hu, Xinbo Gao
To address this, we mask the clothing and color information in the personal attribute description extracted through an attribute detection model.
no code implementations • 20 Dec 2023 • Xingyilang Yin, Xi Yang, Liangchen Liu, Nannan Wang, Xinbo Gao
Additional offsets and modulation scalars are learned on the whole point features, which shift the deformable reference points to the regions of interest.
1 code implementation • 18 Dec 2023 • Decheng Liu, Xijun Wang, Chunlei Peng, Nannan Wang, Ruiming Hu, Xinbo Gao
Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models.
1 code implementation • 17 Dec 2023 • Xiaoqi An, Lin Zhao, Chen Gong, Nannan Wang, Di Wang, Jian Yang
In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?"
1 code implementation • 16 Dec 2023 • Decheng Liu, Xu Luo, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao
In this paper, we propose a novel Symmetrical Bidirectional Knowledge Alignment for zero-shot sketch-based image retrieval (SBKA).
no code implementations • 14 Dec 2023 • Yan Gao, Haojun Xu, Nannan Wang, Jie Li, Xinbo Gao
In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction, improving the graph neural network's feature representation capability.
2 code implementations • 7 Dec 2023 • Chunlei Peng, Huiqing Guo, Decheng Liu, Nannan Wang, Ruimin Hu, Xinbo Gao
Considering the complexity of the quality distribution of both real and fake faces, we propose a novel Deepfake detection framework named DeepFidelity to adaptively distinguish real and fake faces with varying image quality by mining the perceptual forgery fidelity of face images.
no code implementations • 5 Dec 2023 • Guozhang Li, Xinpeng Ding, De Cheng, Jie Li, Nannan Wang, Xinbo Gao
To further clarify the noise of expanded boundaries, we combine mutual learning with a tailored proposal-level contrastive objective to use a learnable approach to harmonize a balance between incomplete yet clean (initial) and comprehensive yet noisy (expanded) boundaries for more precise ones.
no code implementations • 24 Nov 2023 • Ruoyu Zhao, Mingrui Zhu, Shiyin Dong, Nannan Wang, Xinbo Gao
We propose CatVersion, an inversion-based method that learns the personalized concept through a handful of examples.
no code implementations • 15 Nov 2023 • Dongxin Chen, Mingrui Zhu, Nannan Wang, Xinbo Gao
To disentangle the latent codes in the GAN inversion space, we introduce an Identity Disentanglement Module (IDM).
no code implementations • 13 Nov 2023 • Qinlin He, Chunlei Peng, Decheng Liu, Nannan Wang, Xinbo Gao
DeepFake detection is pivotal in personal privacy and public safety.
1 code implementation • 5 Oct 2023 • Nuoyan Zhou, Nannan Wang, Decheng Liu, Dawei Zhou, Xinbo Gao
Deep neural networks are vulnerable to adversarial noise.
Ranked #1 on Adversarial Attack on CIFAR-10 (Attack: AutoAttack metric)
no code implementations • 14 Sep 2023 • Liangchen Liu, Nannan Wang, Dawei Zhou, Xinbo Gao, Decheng Liu, Xi Yang, Tongliang Liu
This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i. e., improving the performance on unseen classes while maintaining the performance on seen classes.
no code implementations • 11 Sep 2023 • Xiao He, Mingrui Zhu, Dongxin Chen, Nannan Wang, Xinbo Gao
In this paper, we unify the task of anonymization and visual identity information hiding and propose a novel face privacy protection method based on diffusion models, dubbed Diff-Privacy.
1 code implementation • ICCV 2023 • Fei Gao, Yifan Zhu, Chang Jiang, Nannan Wang
Besides, different artists may use diverse drawing techniques and create multiple styles of sketches; but the style is globally consistent in a sketch.
1 code implementation • 21 Jul 2023 • Decheng Liu, Tao Chen, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao
Due to the successful development of deep image generation technology, visual data forgery detection would play a more important role in social and economic security.
no code implementations • 18 Jul 2023 • Lin Yuan, Kai Liang, Xiao Pu, Yan Zhang, Jiaxu Leng, Tao Wu, Nannan Wang, Xinbo Gao
This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single lightweight framework.
no code implementations • 6 Jul 2023 • Ruiyang Xia, Decheng Liu, Jie Li, Lin Yuan, Nannan Wang, Xinbo Gao
Advanced manipulation techniques have provided criminals with opportunities to make social panic or gain illicit profits through the generation of deceptive media, such as forged face images.
1 code implementation • NeurIPS 2023 • Yun Yi, Haokui Zhang, Rong Xiao, Nannan Wang, Xiaoyu Wang
It can learn efficient representations from both cell-structured networks and entire networks.
no code implementations • 22 May 2023 • De Cheng, Lingfeng He, Nannan Wang, Shizhou Zhang, Zhen Wang, Xinbo Gao
To this end, we propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters.
no code implementations • 22 May 2023 • De Cheng, Xiaojian Huang, Nannan Wang, Lingfeng He, Zhihui Li, Xinbo Gao
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial for practical applications in video surveillance systems.
no code implementations • 9 May 2023 • Shiyin Dong, Mingrui Zhu, Nannan Wang, Xinbo Gao
Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to the cross-domain nature of sketches and photos, as well as the semantic gap between seen and unseen image distributions.
1 code implementation • 4 May 2023 • Biao Ma, Fei Gao, Chang Jiang, Nannan Wang, Gang Xu
Our motivation is that facial semantic labels are view-consistent and correlate with drawing techniques.
1 code implementation • CVPR 2023 • Guozhang Li, De Cheng, Xinpeng Ding, Nannan Wang, Xiaoyu Wang, Xinbo Gao
For the discriminative objective, we propose a Text-Segment Mining (TSM) mechanism, which constructs a text description based on the action class label, and regards the text as the query to mine all class-related segments.
1 code implementation • 25 Apr 2023 • Guozhang Li, De Cheng, Xinpeng Ding, Nannan Wang, Jie Li, Xinbo Gao
The proposed Bi-SCC firstly adopts a temporal context augmentation to generate an augmented video that breaks the correlation between positive actions and their co-scene actions in the inter-video; Then, a semantic consistency constraint (SCC) is used to enforce the predictions of the original video and augmented video to be consistent, hence suppressing the co-scene actions.
Weakly-supervised Temporal Action Localization Weakly Supervised Temporal Action Localization
1 code implementation • CVPR 2023 • Chang Jiang, Fei Gao, Biao Ma, YuHao Lin, Nannan Wang, Gang Xu
To overcome this challenge, we improve the accuracy of matching on the one hand, and diminish the role of matching in image generation on the other hand.
no code implementations • 28 Jan 2023 • Ruoyu Zhao, Mingrui Zhu, Xiaoyu Wang, Nannan Wang
GPD contains two models: a teacher network with GAN Prior and a student network that fulfills end-to-end translation.
no code implementations • 24 Jan 2023 • Xiao He, Mingrui Zhu, Nannan Wang, Xinbo Gao, Heng Yang
To address this issue, we propose a novel font generation approach by learning the Difference between different styles and the Similarity of the same style (DS-Font).
1 code implementation • 30 Dec 2022 • Decheng Liu, Zeyang Zheng, Chunlei Peng, Yukai Wang, Nannan Wang, Xinbo Gao
Face forgery detection plays an important role in personal privacy and social security.
no code implementations • ICCV 2023 • Mingrui Zhu, Xiao He, Nannan Wang, Xiaoyu Wang, Xinbo Gao
In this paper, we propose a novel all-to-key attention mechanism -- each position of content features is matched to stable key positions of style features -- that is more in line with the characteristics of style transfer.
no code implementations • 30 Nov 2022 • De Cheng, Haichun Tai, Nannan Wang, Zhen Wang, Xinbo Gao
In this paper, we propose a Neighbour Consistency guided Pseudo Label Refinement (NCPLR) framework, which can be regarded as a transductive form of label propagation under the assumption that the prediction of each example should be similar to its nearest neighbours'.
1 code implementation • 27 Nov 2022 • Kun Cheng, Xiaodong Cun, Yong Zhang, Menghan Xia, Fei Yin, Mingrui Zhu, Xuan Wang, Jue Wang, Nannan Wang
Our system disentangles this objective into three sequential tasks: (1) face video generation with a canonical expression; (2) audio-driven lip-sync; and (3) face enhancement for improving photo-realism.
1 code implementation • CVPR 2023 • Yun Yi, Haokui Zhang, Wenze Hu, Nannan Wang, Xiaoyu Wang
In this paper, we propose a neural architecture representation model that can be used to estimate these attributes holistically.
1 code implementation • NIPS 2022 • De Cheng, Yixiong Ning, Nannan Wang, Xinbo Gao, Heng Yang, Yuxuan Du, Bo Han, Tongliang Liu
We show that the cycle-consistency regularization helps to minimize the volume of the transition matrix T indirectly without exploiting the estimated noisy class posterior, which could further encourage the estimated transition matrix T to converge to its optimal solution.
1 code implementation • 18 Oct 2022 • Decheng Liu, Zhan Dang, Chunlei Peng, Yu Zheng, Shuang Li, Nannan Wang, Xinbo Gao
Experiments conducted on publicly available face forgery detection datasets prove the superior performance of the proposed FedForgery.
no code implementations • 4 Oct 2022 • Chaojian Yu, Dawei Zhou, Li Shen, Jun Yu, Bo Han, Mingming Gong, Nannan Wang, Tongliang Liu
Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness disparity between natural and robust accuracies, which deviates from robust network's desideratum.
1 code implementation • 25 Jul 2022 • Dawei Zhou, Nannan Wang, Xinbo Gao, Bo Han, Xiaoyu Wang, Yibing Zhan, Tongliang Liu
To alleviate this negative effect, in this paper, we investigate the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and propose an adversarial defense method.
1 code implementation • 12 Jul 2022 • Decheng Liu, Weijie He, Chunlei Peng, Nannan Wang, Jie Li, Xinbo Gao
The multiple branches transformer is employed to explore the inter-correlation between different attributes in similar semantic regions for attribute feature learning.
no code implementations • 5 Jul 2022 • Yukai Wang, Chunlei Peng, Decheng Liu, Nannan Wang, Xinbo Gao
In recent years, with the rapid development of face editing and generation, more and more fake videos are circulating on social media, which has caused extreme public concerns.
no code implementations • CVPR 2022 • De Cheng, Tongliang Liu, Yixiong Ning, Nannan Wang, Bo Han, Gang Niu, Xinbo Gao, Masashi Sugiyama
In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers.
no code implementations • 29 Mar 2022 • De Cheng, Yan Li, Dingwen Zhang, Nannan Wang, Xinbo Gao, Jiande Sun
To properly address this problem, we propose a novel density-variational learning framework to improve the robustness of the image dehzing model assisted by a variety of negative hazy images, to better deal with various complex hazy scenarios.
1 code implementation • CVPR 2022 • Hangyu Li, Nannan Wang, Xi Yang, Xiaoyu Wang, Xinbo Gao
In this paper, we learn an Adaptive Confidence Margin (Ada-CM) to fully leverage all unlabeled data for semi-supervised deep facial expression recognition.
Facial Expression Recognition Facial Expression Recognition (FER)
1 code implementation • 4 Mar 2022 • Mingrui Zhu, Yun Yi, Nannan Wang, Xiaoyu Wang, Xinbo Gao
The large discrepancy between the source non-makeup image and the reference makeup image is one of the key challenges in makeup transfer.
no code implementations • 29 Sep 2021 • Dawei Zhou, Nannan Wang, Bo Han, Tongliang Liu
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks.
no code implementations • 29 Sep 2021 • De Cheng, Jingyu Zhou, Nannan Wang, Xinbo Gao
However, since person Re-Id is an open-set problem, the clustering based methods often leave out lots of outlier instances or group the instances into the wrong clusters, thus they can not make full use of the training samples as a whole.
1 code implementation • 22 Sep 2021 • Yan Li, De Cheng, Jiande Sun, Dingwen Zhang, Nannan Wang, Xinbo Gao
In this paper, we propose a single image dehazing method with an independent Detail Recovery Network (DRN), which considers capturing the details from the input image over a separate network and then integrates them into a coarse dehazed image.
1 code implementation • 21 Sep 2021 • Dawei Zhou, Nannan Wang, Bo Han, Tongliang Liu
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks.
no code implementations • ICCV 2021 • Xinpeng Ding, Nannan Wang, Shiwei Zhang, De Cheng, Xiaomeng Li, Ziyuan Huang, Mingqian Tang, Xinbo Gao
The contrastive objective aims to learn effective representations by contrastive learning, while the caption objective can train a powerful video encoder supervised by texts.
no code implementations • CVPR 2022 • Zhaoqing Wang, Qiang Li, Guoxin Zhang, Pengfei Wan, Wen Zheng, Nannan Wang, Mingming Gong, Tongliang Liu
By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks.
no code implementations • 10 Jul 2021 • Xiaobo Xia, Shuo Shan, Mingming Gong, Nannan Wang, Fei Gao, Haikun Wei, Tongliang Liu
Estimating the kernel mean in a reproducing kernel Hilbert space is a critical component in many kernel learning algorithms.
no code implementations • 10 Jun 2021 • Dawei Zhou, Nannan Wang, Xinbo Gao, Bo Han, Jun Yu, Xiaoyu Wang, Tongliang Liu
However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting.
no code implementations • 9 Jun 2021 • Dawei Zhou, Tongliang Liu, Bo Han, Nannan Wang, Chunlei Peng, Xinbo Gao
However, given the continuously evolving attacks, models trained on seen types of adversarial examples generally cannot generalize well to unseen types of adversarial examples.
no code implementations • ICCV 2021 • Dawei Zhou, Nannan Wang, Chunlei Peng, Xinbo Gao, Xiaoyu Wang, Jun Yu, Tongliang Liu
Then, we train a denoising model to minimize the distances between the adversarial examples and the natural examples in the class activation feature space.
2 code implementations • CVPR 2021 • Tianwei Lin, Zhuoqi Ma, Fu Li, Dongliang He, Xin Li, Errui Ding, Nannan Wang, Jie Li, Xinbo Gao
Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).
no code implementations • 1 Jan 2021 • Dawei Zhou, Tongliang Liu, Bo Han, Nannan Wang, Xinbo Gao
Motivated by this observation, we propose a defense framework ADD-Defense, which extracts the invariant information called \textit{perturbation-invariant representation} (PIR) to defend against widespread adversarial examples.
no code implementations • ICLR 2021 • Xiaobo Xia, Tongliang Liu, Bo Han, Chen Gong, Nannan Wang, ZongYuan Ge, Yi Chang
The \textit{early stopping} method therefore can be exploited for learning with noisy labels.
Ranked #32 on Image Classification on mini WebVision 1.0 (ImageNet Top-1 Accuracy metric)
no code implementations • ICCV 2021 • Ziyu Wei, Xi Yang, Nannan Wang, Xinbo Gao
Visible infrared person re-identification (VI-REID) aims to match pedestrian images between the daytime visible and nighttime infrared camera views.
no code implementations • 2 Dec 2020 • Xiaobo Xia, Tongliang Liu, Bo Han, Nannan Wang, Jiankang Deng, Jiatong Li, Yinian Mao
The traditional transition matrix is limited to model closed-set label noise, where noisy training data has true class labels within the noisy label set.
no code implementations • 28 Sep 2020 • Songhua Wu, Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Nannan Wang, Haifeng Liu, Gang Niu
It is worthwhile to perform the transformation: We prove that the noise rate for the noisy similarity labels is lower than that of the noisy class labels, because similarity labels themselves are robust to noise.
no code implementations • 24 Sep 2020 • Jingda Guo, Dominic Carrillo, Sihai Tang, Qi Chen, Qing Yang, Song Fu, Xi Wang, Nannan Wang, Paparao Palacharla
To reduce the amount of transmitted data, feature map based fusion is recently proposed as a practical solution to cooperative 3D object detection by autonomous vehicles.
no code implementations • 3 Jul 2020 • Xinpeng Ding, Nannan Wang, Xinbo Gao, Jie Li, Xiaoyu Wang, Tongliang Liu
Specifically, we devise a partial segment loss regarded as a loss sampling to learn integral action parts from labeled segments.
Weakly-supervised Temporal Action Localization Weakly Supervised Temporal Action Localization
1 code implementation • NeurIPS 2020 • Xiaobo Xia, Tongliang Liu, Bo Han, Nannan Wang, Mingming Gong, Haifeng Liu, Gang Niu, DaCheng Tao, Masashi Sugiyama
Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise.
no code implementations • 14 Jun 2020 • Songhua Wu, Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Nannan Wang, Haifeng Liu, Gang Niu
To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class label or not.
no code implementations • 25 May 2020 • Bing Cao, Nannan Wang, Xinbo Gao, Jie Li, Zhifeng Li
Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios.
no code implementations • 16 Feb 2020 • Jingwei Xin, Nannan Wang, Xinrui Jiang, Jie Li, Xinbo Gao, Zhifeng Li
In the SR processing, we first generated a group of FACs from the input LR face, and then reconstructed the HR face from this group of FACs.
no code implementations • 16 Feb 2020 • Songhua Wu, Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Nannan Wang, Haifeng Liu, Gang Niu
We further estimate the transition matrix from only noisy data and build a novel learning system to learn a classifier which can assign noise-free class labels for instances.
no code implementations • 15 Feb 2020 • Jingwei Xin, Nannan Wang, Jie Li, Xinbo Gao, Zhifeng Li
Current state-of-the-art CNN methods usually treat the VSR problem as a large number of separate multi-frame super-resolution tasks, at which a batch of low resolution (LR) frames is utilized to generate a single high resolution (HR) frame, and running a slide window to select LR frames over the entire video would obtain a series of HR frames.
1 code implementation • NeurIPS 2019 • Xiaobo Xia, Tongliang Liu, Nannan Wang, Bo Han, Chen Gong, Gang Niu, Masashi Sugiyama
Existing theories have shown that the transition matrix can be learned by exploiting \textit{anchor points} (i. e., data points that belong to a specific class almost surely).
Ranked #18 on Learning with noisy labels on CIFAR-10N-Random3
no code implementations • 23 May 2018 • Xi Yang, Xinbo Gao, Bin Song, Nannan Wang, Dong Yang
In this paper, we aim to explore a new search method for images captured with circular fisheye lens, especially the aurora images.
no code implementations • 8 Jan 2017 • Nannan Wang, Xinbo Gao, Jie Li
The most time-consuming or main computation complexity for exemplar-based face sketch synthesis methods lies in the neighbor selection process.
no code implementations • 1 Jul 2016 • Chunlei Peng, Xinbo Gao, Nannan Wang, Jie Li
An adaptive sparse graphical representation scheme is designed to represent heterogeneous face images, where a Markov networks model is constructed to generate adaptive sparse vectors.
no code implementations • 25 Mar 2016 • Nannan Wang, Jie Li, Leiyu Sun, Bin Song, Xinbo Gao
In this paper, we proposed a synthesized face sketch recognition framework based on full-reference image quality assessment metrics.
no code implementations • 2 Mar 2015 • Chunlei Peng, Xinbo Gao, Nannan Wang, Jie Li
Heterogeneous face recognition (HFR) refers to matching face images acquired from different sources (i. e., different sensors or different wavelengths) for identification.
no code implementations • 4 Oct 2014 • Nannan Wang, Xinbo Gao, DaCheng Tao, Xuelong. Li
CLM-based methods consist of a shape model and a number of local experts, each of which is utilized to detect a facial feature point.