1 code implementation • 31 Mar 2024 • Haolin Qin, Tingfa Xu, Peifu Liu, Jingxuan Xu, Jianan Li
To address these challenges, we propose a novel approach termed the Distilled Mixed Spectral-Spatial Network (DMSSN), comprising a Distilled Spectral Encoding process and a Mixed Spectral-Spatial Transformer (MSST) feature extraction network.
no code implementations • 7 Mar 2024 • Xiaoying Yuan, Tingfa Xu, Xincong Liu, Ying Wang, Haolin Qin, Yuqiang Fang, Jianan Li
This module leverages temporal information to refresh the template feature, yielding a more precise correlation map.
no code implementations • 22 Jan 2024 • Shenwang Jiang, Jianan Li, Ying Wang, Wenxuan Wu, Jizhou Zhang, Bo Huang, Tingfa Xu
Noisy labels, inevitably existing in pseudo segmentation labels generated from weak object-level annotations, severely hampers model optimization for semantic segmentation.
1 code implementation • 22 Jan 2024 • Jianan Li, Jie Wang, Tingfa Xu
Efficient analysis of point clouds holds paramount significance in real-world 3D applications.
no code implementations • 22 Jan 2024 • Jianan Li, Shaocong Dong, Lihe Ding, Tingfa Xu
To mitigate the computational complexity associated with applying a window-based transformer in 3D voxel space, we introduce a novel Chessboard Sampling strategy and implement voxel sampling and gathering operations sparsely using a hash map.
1 code implementation • 14 Dec 2023 • Haolin Qin, Daquan Zhou, Tingfa Xu, Ziyang Bian, Jianan Li
Accordingly, we propose a novel factorization self-attention mechanism (FaSA) that enjoys both the advantages of local window cost and long-range dependency modeling capability.
no code implementations • 11 Dec 2023 • Xincong Liu, Tingfa Xu, Ying Wang, Zhinong Yu, Xiaoying Yuan, Haolin Qin, Jianan Li
At the same time, the appearance discriminator employs an online adaptive template-update strategy to ensure that the collected multiple templates remain reliable and diverse, allowing them to closely follow rapid changes in the target's appearance and suppress background interference during tracking.
1 code implementation • 2 Dec 2023 • Peifu Liu, Tingfa Xu, Huan Chen, Shiyun Zhou, Haolin Qin, Jianan Li
The Spectral Saliency approximates the region of salient objects, while the Spectral Edge captures edge information of salient objects.
no code implementations • 2 Dec 2023 • Huan Chen, Wangcai Zhao, Tingfa Xu, Shiyun Zhou, Peifu Liu, Jianan Li
The Fourier coordinate encoder enhances the SINR's ability to emphasize high-frequency components, while the spectral scale factor module guides the SINR to adapt to the variable number of spectral channels.
1 code implementation • ICCV 2023 • Jie Wang, Lihe Ding, Tingfa Xu, Shaocong Dong, Xinli Xu, Long Bai, Jianan Li
Robust 3D perception under corruption has become an essential task for the realm of 3D vision.
1 code implementation • 6 Feb 2023 • Shiyun Zhou, Tingfa Xu, Shaocong Dong, Jianan Li
The regional dynamic block guides the network to adjust the transformation domain for different regions.
no code implementations • CVPR 2023 • Shiqi Huang, Tingfa Xu, Ning Shen, Feng Mu, Jianan Li
The existing few-shot medical segmentation networks share the same practice that the more prototypes, the better performance.
no code implementations • 18 Dec 2022 • Jianan Li, Shenwang Jiang, Liqiang Song, Peiran Peng, Feng Mu, Hui Li, Peng Jiang, Tingfa Xu
Hence, the timely and accurate detection of surface defects is crucial for FAST's stable operation.
1 code implementation • 22 Nov 2022 • Shenwang Jiang, Jianan Li, Jizhou Zhang, Ying Wang, Tingfa Xu
Label noise and class imbalance commonly coexist in real-world data.
Ranked #6 on Learning with noisy labels on ANIMAL
no code implementations • 22 Sep 2022 • Xinli Xu, Shaocong Dong, Lihe Ding, Jie Wang, Tingfa Xu, Jianan Li
Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm which merely relies on LiDAR point clouds for 3D proposal refinement.
no code implementations • 26 Jan 2022 • Shiqi Huang, Jianan Li, Yuze Xiao, Ning Shen, Tingfa Xu
Automatic diabetic retinopathy (DR) lesions segmentation makes great sense of assisting ophthalmologists in diagnosis.
1 code implementation • 30 Dec 2021 • Shenwang Jiang, Jianan Li, Ying Wang, Bo Huang, Zhang Zhang, Tingfa Xu
In practice, however, biased samples with corrupted labels and of tailed classes commonly co-exist in training data.
no code implementations • 28 Nov 2021 • Jie Wang, Jianan Li, Lihe Ding, Ying Wang, Tingfa Xu
Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds.
no code implementations • 15 Oct 2021 • Ying Wang, Tingfa Xu, Jianan Li, Shenwang Jiang, Junjie Chen
Through experiments we find that, without regression, the performance could be equally promising as long as we delicately design the network to suit the training objective.
no code implementations • 30 Apr 2021 • Xinglong Sun, Guangliang Han, Lihong Guo, Tingfa Xu, Jianan Li, Peixun Liu
Offline Siamese networks have achieved very promising tracking performance, especially in accuracy and efficiency.
no code implementations • 11 Sep 2020 • Jianan Li, Jimei Yang, Jianming Zhang, Chang Liu, Christina Wang, Tingfa Xu
In this paper, we introduce Attribute-conditioned Layout GAN to incorporate the attributes of design elements for graphic layout generation by forcing both the generator and the discriminator to meet attribute conditions.
1 code implementation • ICCV 2019 • Ziyi Shen, Wenguan Wang, Xiankai Lu, Jianbing Shen, Haibin Ling, Tingfa Xu, Ling Shao
This paper proposes a human-aware deblurring model that disentangles the motion blur between foreground (FG) humans and background (BG).
no code implementations • 19 Jan 2020 • Ziyi Shen, Wei-Sheng Lai, Tingfa Xu, Jan Kautz, Ming-Hsuan Yang
Specifically, we first use a coarse deblurring network to reduce the motion blur on the input face image.
1 code implementation • ICLR 2019 • Jianan Li, Tingfa Xu, Jianming Zhang, Aaron Hertzmann, Jimei Yang
Layouts are important for graphic design and scene generation.
1 code implementation • 21 Jan 2019 • Jianan Li, Jimei Yang, Aaron Hertzmann, Jianming Zhang, Tingfa Xu
Layout is important for graphic design and scene generation.
no code implementations • 3 Jul 2018 • Jie Guo, Tingfa Xu, Shenwang Jiang, Ziyi Shen
Deep convolutional neural networks (CNNs) have dominated many computer vision domains because of their great power to extract good features automatically.
no code implementations • CVPR 2018 • Ziyi Shen, Wei-Sheng Lai, Tingfa Xu, Jan Kautz, Ming-Hsuan Yang
In this paper, we present an effective and efficient face deblurring algorithm by exploiting semantic cues via deep convolutional neural networks (CNNs).
no code implementations • CVPR 2017 • Jianan Li, Xiaodan Liang, Yunchao Wei, Tingfa Xu, Jiashi Feng, Shuicheng Yan
In this work, we address the small object detection problem by developing a single architecture that internally lifts representations of small objects to "super-resolved" ones, achieving similar characteristics as large objects and thus more discriminative for detection.
no code implementations • 18 Aug 2016 • Jianan Li, Xiaodan Liang, Jianshu Li, Tingfa Xu, Jiashi Feng, Shuicheng Yan
Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately.
no code implementations • 24 Mar 2016 • Jianan Li, Yunchao Wei, Xiaodan Liang, Jian Dong, Tingfa Xu, Jiashi Feng, Shuicheng Yan
We provide preliminary answers to these questions through developing a novel Attention to Context Convolution Neural Network (AC-CNN) based object detection model.
no code implementations • 28 Oct 2015 • Jianan Li, Xiaodan Liang, ShengMei Shen, Tingfa Xu, Jiashi Feng, Shuicheng Yan
Taking pedestrian detection as an example, we illustrate how we can leverage this philosophy to develop a Scale-Aware Fast R-CNN (SAF R-CNN) framework.
Ranked #23 on Pedestrian Detection on Caltech