no code implementations • ICML 2020 • Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan YAO
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.
no code implementations • 11 Feb 2025 • Sixiao Zheng, Zimian Peng, Yanpeng Zhou, Yi Zhu, Hang Xu, Xiangru Huang, Yanwei Fu
In this paper, we introduce VidCRAFT3, a novel framework for precise image-to-video generation that enables control over camera motion, object motion, and lighting direction simultaneously.
1 code implementation • 9 Feb 2025 • Kaizhen Zhu, Mokai Pan, Yuexin Ma, Yanwei Fu, Jingyi Yu, Jingya Wang, Ye Shi
We demonstrate that existing diffusion bridges employing Doob's $h$-transform constitute a special case of our framework, emerging when the terminal penalty coefficient in the SOC cost function tends to infinity.
1 code implementation • 20 Jan 2025 • Chang Wan, Ke Fan, Xinwei Sun, Yanwei Fu, MingLu Li, Yunliang Jiang, ZhongLong Zheng
To address these challenges, we propose a novel Lipschitz-constrained Functional Gradient GANs learning (Li-CFG) method to stabilize the training of GAN and provide a theoretical foundation for effectively increasing the diversity of synthetic samples by reducing the neighborhood size of the latent vector.
no code implementations • 16 Jan 2025 • Yanwei Fu, Jianxiong Gao, Baofeng Yang, Jianfeng Feng
By combining subjective dream experiences with objective neurophysiological data, we aim to understand the visual aspects of dreams and create complete video narratives.
no code implementations • 6 Jan 2025 • Yizhuo Ding, Ke Fan, Yikai Wang, Xinwei Sun, Yanwei Fu
Therefore, the solution path identifies a Transformer weight family with various sparsity levels, offering greater flexibility and customization.
no code implementations • 3 Dec 2024 • Junqiu Yu, Xinlin Ren, Yongchong Gu, Haitao Lin, Tianyu Wang, Yi Zhu, Hang Xu, Yu-Gang Jiang, xiangyang xue, Yanwei Fu
Language-guided robotic grasping is a rapidly advancing field where robots are instructed using human language to grasp specific objects.
no code implementations • 2 Dec 2024 • Lingyun Zhang, Yu Xie, Yanwei Fu, Ping Chen
As large-scale diffusion models continue to advance, they excel at producing high-quality images but often generate unwanted content, such as sexually explicit or violent content.
no code implementations • 28 Nov 2024 • Yuqian Fu, Runze Wang, Yanwei Fu, Danda Pani Paudel, Xuanjing Huang, Luc van Gool
In this paper, we focus on the Ego-Exo Object Correspondence task, an emerging challenge in the field of computer vision that aims to map objects across ego-centric and exo-centric views.
1 code implementation • 25 Nov 2024 • Chenjie Cao, Chaohui Yu, Shang Liu, Fan Wang, xiangyang xue, Yanwei Fu
We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks.
1 code implementation • 15 Nov 2024 • Boyuan Jiang, Xiaobin Hu, Donghao Luo, Qingdong He, Chengming Xu, Jinlong Peng, Jiangning Zhang, Chengjie Wang, Yunsheng Wu, Yanwei Fu
Although image-based virtual try-on has made considerable progress, emerging approaches still encounter challenges in producing high-fidelity and robust fitting images across diverse scenarios.
Ranked #2 on
Virtual Try-on
on VITON-HD
no code implementations • 27 Sep 2024 • Zhiling Zhou, Zirui Liu, Chengming Xu, Yanwei Fu, Xinwei Sun
While neural networks have made significant strides in many AI tasks, they remain vulnerable to a range of noise types, including natural corruptions, adversarial noise, and low-resolution artifacts.
no code implementations • 17 Sep 2024 • Jianxiong Gao, Yanwei Fu, Yuqian Fu, Yun Wang, Xuelin Qian, Jianfeng Feng
Moreover, we propose MinD-3D++, a novel framework for decoding textured 3D visual information from fMRI signals.
no code implementations • 5 Sep 2024 • Weipeng Tan, Chuming Lin, Chengming Xu, Xiaozhong Ji, Junwei Zhu, Chengjie Wang, Yunsheng Wu, Yanwei Fu
Specifically, we first introduce the novel probabilistic style prior learning to model the intrinsic style as a Gaussian distribution using facial expressions and audio embedding.
no code implementations • 15 Aug 2024 • Tianyu Wang, Haitao Lin, Junqiu Yu, Yanwei Fu
This paper investigates the task of the open-ended interactive robotic manipulation on table-top scenarios.
no code implementations • 15 Aug 2024 • Chenjie Cao, Chaohui Yu, Fan Wang, xiangyang xue, Yanwei Fu
Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements.
no code implementations • 6 Aug 2024 • Jinyu Zhang, Yongchong Gu, Jianxiong Gao, Haitao Lin, Qiang Sun, Xinwei Sun, xiangyang xue, Yanwei Fu
This paper addresses the challenge of perceiving complete object shapes through visual perception.
1 code implementation • 4 Aug 2024 • Xinlin Ren, Chenjie Cao, Yanwei Fu, xiangyang xue
Additionally, we examine the impact of varying feature resolutions and evaluate both pixel-wise and patch-wise consistent losses, providing insights into effective strategies for improving NSR performance.
1 code implementation • 25 Jul 2024 • YiFan Li, Yikai Wang, Yanwei Fu, Dongyu Ru, Zheng Zhang, Tong He
On the other hand, lexical representation, a vector whose element represents the similarity between the sample and a word from the vocabulary, is a natural sparse representation and interpretable, providing exact matches for individual words.
no code implementations • 13 Jul 2024 • Sixiao Zheng, Yanwei Fu
To address these issues, we propose ContextualStory, a novel framework designed to generate coherent story frames and extend frames for story continuation.
Ranked #1 on
Story Visualization
on Pororo
no code implementations • 26 Jun 2024 • Lingjie Kong, Qiaoling Wei, Chengming Xu, Han Chen, Yanwei Fu
In response to this challenge, we propose a novel model named EFCNet for small object segmentation in medical images.
2 code implementations • 17 Jun 2024 • Lingjie Kong, Kai Wu, Xiaobin Hu, Wenhui Han, Jinlong Peng, Chengming Xu, Donghao Luo, Mengtian Li, Jiangning Zhang, Chengjie Wang, Yanwei Fu
The primary issue of promoting zero-shot object customization from specific domains to the general domain is to establish a large-scale general ID dataset for model pre-training, which is time-consuming and labor-intensive.
1 code implementation • CVPR 2024 • Ke Fan, Zechen Bai, Tianjun Xiao, Tong He, Max Horn, Yanwei Fu, Francesco Locatello, Zheng Zhang
Moreover, our analysis substantiates that our method exhibits the capability to dynamically adapt the slot number according to each instance's complexity, offering the potential for further exploration in slot attention research.
no code implementations • 30 May 2024 • Jianxiong Gao, Xuelin Qian, Longfei Liang, Junwei Han, Yanwei Fu
The multi-scale features from the image branch guide the hyper transformer in learning shape priors and in generating the weights for dynamic convolution tailored to each instance.
no code implementations • 28 May 2024 • Qilin Wang, Zhengkai Jiang, Chengming Xu, Jiangning Zhang, Yabiao Wang, Xinyi Zhang, Yun Cao, Weijian Cao, Chengjie Wang, Yanwei Fu
This enables accurate alignment of pose and shape in the generated videos, providing a robust framework capable of handling a wide range of body shapes and dynamic hand movements.
no code implementations • 28 May 2024 • Jingwei Xu, Yikai Wang, Yiqun Zhao, Yanwei Fu, Shenghua Gao
The mesh representation of the empty street can be extracted for further applications.
no code implementations • 26 May 2024 • Qizao Wang, Xuelin Qian, Bin Li, Yanwei Fu, xiangyang xue
To tackle the challenges of knowledge granularity mismatch and knowledge presentation mismatch that occurred in LReID-Hybrid, we take advantage of the consistency and generalization of the text space, and propose a novel framework, dubbed $Teata$, to effectively align, transfer and accumulate knowledge in an "image-text-image" closed loop.
1 code implementation • 26 May 2024 • Qizao Wang, Xuelin Qian, Bin Li, Lifeng Chen, Yanwei Fu, xiangyang xue
Specifically, we propose the Content and Salient Semantics Collaboration (CSSC) framework, facilitating cross-parallel semantics interaction and refinement.
Ranked #4 on
Person Re-Identification
on LTCC
no code implementations • 24 May 2024 • Chengming Xu, Chen Liu, Yikai Wang, Yuan YAO, Yanwei Fu
Visual In-Context Learning (VICL) is a prevailing way to transfer visual foundation models to new tasks by leveraging contextual information contained in in-context examples to enhance learning and prediction of query sample.
no code implementations • 24 May 2024 • Chengming Xu, Kai Hu, Qilin Wang, Donghao Luo, Jiangning Zhang, Xiaobin Hu, Yanwei Fu, Chengjie Wang
Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images.
no code implementations • 6 May 2024 • Hangyu Lin, Chen Liu, Chengming Xu, Zhengqi Gao, Yanwei Fu, Yuan YAO
For instance, one typically aims to minimize the L2 distance or contrastive loss between the learned features of pairs of samples in the source (e. g. image) and the target (e. g. sketch) modalities.
no code implementations • CVPR 2024 • Qiaole Dong, Yanwei Fu
To this end, we present MemFlow, a real-time method for optical flow estimation and prediction with memory.
no code implementations • 27 Mar 2024 • Jingyang Huo, Yikai Wang, Xuelin Qian, Yun Wang, Chong Li, Jianfeng Feng, Yanwei Fu
Recent fMRI-to-image approaches mainly focused on associating fMRI signals with specific conditions of pre-trained diffusion models.
no code implementations • 26 Mar 2024 • Qilin Wang, Jiangning Zhang, Chengming Xu, Weijian Cao, Ying Tai, Yue Han, Yanhao Ge, Hong Gu, Chengjie Wang, Yanwei Fu
Facial Appearance Editing (FAE) aims to modify physical attributes, such as pose, expression and lighting, of human facial images while preserving attributes like identity and background, showing great importance in photograph.
no code implementations • 20 Mar 2024 • Shijie Zhang, Boyan Jiang, Keke He, Junwei Zhu, Ying Tai, Chengjie Wang, yinda zhang, Yanwei Fu
Pixel2Mesh (P2M) is a classical approach for reconstructing 3D shapes from a single color image through coarse-to-fine mesh deformation.
no code implementations • 24 Feb 2024 • Sixiao Zheng, Jingyang Huo, Yu Wang, Yanwei Fu
We propose an Intelligent Director framework, utilizing LENS to generate descriptions for images and video frames and combining ChatGPT to generate coherent captions while recommending appropriate music names.
no code implementations • 19 Feb 2024 • Xuelin Qian, Yu Wang, Simian Luo, yinda zhang, Ying Tai, Zhenyu Zhang, Chengjie Wang, xiangyang xue, Bo Zhao, Tiejun Huang, Yunsheng Wu, Yanwei Fu
In this paper, we extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
1 code implementation • 5 Feb 2024 • Yuqian Fu, Yu Wang, Yixuan Pan, Lian Huai, Xingyu Qiu, Zeyu Shangguan, Tong Liu, Yanwei Fu, Luc van Gool, Xingqun Jiang
This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples.
Ranked #1 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Cross-Domain Few-Shot
Cross-Domain Few-Shot Object Detection
+3
1 code implementation • 30 Jan 2024 • Yikai Wang, Chenjie Cao, Ke Fan, Qiaole Dong, YiFan Li, xiangyang xue, Yanwei Fu
To assess SEELE's effectiveness in subject repositioning, we assemble a real-world subject repositioning dataset called ReS.
Ranked #2 on
Image Inpainting
on Places2
1 code implementation • 22 Jan 2024 • Chenjie Cao, Xinlin Ren, Yanwei Fu
Recent advancements in learning-based Multi-View Stereo (MVS) methods have prominently featured transformer-based models with attention mechanisms.
Ranked #1 on
Point Clouds
on Tanks and Temples
1 code implementation • CVPR 2024 • Ke Fan, Tong Liu, Xingyu Qiu, Yikai Wang, Lian Huai, Zeyu Shangguan, Shuang Gou, Fengjian Liu, Yuqian Fu, Yanwei Fu, Xingqun Jiang
We conduct a thorough investigation theoretically and empirically to analyze and understand the meaning of such a linear trend in OOD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
1 code implementation • 30 Dec 2023 • Yilan Dong, Chunlin Yu, Ruiyang Ha, Ye Shi, Yuexin Ma, Lan Xu, Yanwei Fu, Jingya Wang
Existing gait recognition benchmarks mostly include minor clothing variations in the laboratory environments, but lack persistent changes in appearance over time and space.
no code implementations • 12 Dec 2023 • Jianxiong Gao, Yuqian Fu, Yun Wang, Xuelin Qian, Jianfeng Feng, Yanwei Fu
In this paper, we introduce Recon3DMind, an innovative task aimed at reconstructing 3D visuals from Functional Magnetic Resonance Imaging (fMRI) signals, marking a significant advancement in the fields of cognitive neuroscience and computer vision.
1 code implementation • 4 Dec 2023 • Qiaole Dong, Bo Zhao, Yanwei Fu
Recently, Google proposes DDVM which for the first time demonstrates that a general diffusion model for image-to-image translation task works impressively well on optical flow estimation task without any specific designs like RAFT.
no code implementations • 1 Nov 2023 • Xuelin Qian, Yun Wang, Jingyang Huo, Jianfeng Feng, Yanwei Fu
The exploration of brain activity and its decoding from fMRI data has been a longstanding pursuit, driven by its potential applications in brain-computer interfaces, medical diagnostics, and virtual reality.
no code implementations • 29 Sep 2023 • Yong Wu, Mingzhou Liu, Jing Yan, Yanwei Fu, Shouyan Wang, Yizhou Wang, Xinwei Sun
To accommodate these scenarios, we consider a new setting dubbed as multiple treatments and multiple outcomes.
1 code implementation • ICCV 2023 • Ke Fan, Jingshi Lei, Xuelin Qian, Miaopeng Yu, Tianjun Xiao, Tong He, Zheng Zhang, Yanwei Fu
Furthermore, we propose a multi-view fusion layer based temporal module which is equipped with a set of object slots and interacts with features from different views by attention mechanism to fulfill sufficient object representation completion.
1 code implementation • 22 Sep 2023 • Yong Wu, Yanwei Fu, Shouyan Wang, Xinwei Sun
To address these challenges, we propose a kernel-based DR estimator that can well handle continuous treatments.
1 code implementation • ICCV 2023 • Ke Fan, Zechen Bai, Tianjun Xiao, Dominik Zietlow, Max Horn, Zixu Zhao, Carl-Johann Simon-Gabriel, Mike Zheng Shou, Francesco Locatello, Bernt Schiele, Thomas Brox, Zheng Zhang, Yanwei Fu, Tong He
In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization.
1 code implementation • ICCV 2023 • Zixu Zhao, Jiaze Wang, Max Horn, Yizhuo Ding, Tong He, Zechen Bai, Dominik Zietlow, Carl-Johann Simon-Gabriel, Bing Shuai, Zhuowen Tu, Thomas Brox, Bernt Schiele, Yanwei Fu, Francesco Locatello, Zheng Zhang, Tianjun Xiao
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines.
1 code implementation • ICCV 2023 • Jianxiong Gao, Xuelin Qian, Yikai Wang, Tianjun Xiao, Tong He, Zheng Zhang, Yanwei Fu
To address this issue, we propose a convolution refine module to inject fine-grained information and provide a more precise amodal object segmentation based on visual features and coarse-predicted segmentation.
no code implementations • 30 Aug 2023 • Tianyu Wang, YiFan Li, Haitao Lin, xiangyang xue, Yanwei Fu
The target instruction is then forwarded to a visual grounding system for object pose and size estimation, following which the robot grasps the object accordingly.
no code implementations • 21 Aug 2023 • Qizao Wang, Xuelin Qian, Bin Li, Yanwei Fu, xiangyang xue
In this paper, we rethink the role of the classifier in person Re-ID, and advocate a new perspective to conceive the classifier as a projection from image features to class prototypes.
Ranked #2 on
Person Re-Identification
on CUHK03
1 code implementation • 21 Aug 2023 • Qizao Wang, Xuelin Qian, Bin Li, xiangyang xue, Yanwei Fu
Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and limited training samples.
Ranked #3 on
Person Re-Identification
on LTCC
1 code implementation • 6 Aug 2023 • Linbo Wang, Jing Wu, Xianyong Fang, Zhengyi Liu, Chenjie Cao, Yanwei Fu
First, we propose a Local Feature Consensus (LFC) plugin block to augment the features of existing models.
no code implementations • 20 Jun 2023 • Yu Wang, Xuelin Qian, Jingyang Huo, Tiejun Huang, Bo Zhao, Yanwei Fu
Through the adaptation of the Auto-Regressive model and the utilization of large language models, we have developed a remarkable model with an astounding 3. 6 billion trainable parameters, establishing it as the largest 3D shape generation model to date, named Argus-3D.
1 code implementation • CVPR 2023 • Jingyang Huo, Qiang Sun, Boyan Jiang, Haitao Lin, Yanwei Fu
Technically, we introduce a two-stage module that combine local slot attention and CLIP model to produce geometry-enhanced representation from such input.
3 code implementations • CVPR 2024 • Chenjie Cao, Yunuo Cai, Qiaole Dong, Yikai Wang, Yanwei Fu
As an exemplar, we leverage LeftRefill to address two different challenges: reference-guided inpainting and novel view synthesis, based on the pre-trained StableDiffusion.
1 code implementation • 2 May 2023 • Yang Zhang, Le Cheng, Yuting Peng, Chengming Xu, Yanwei Fu, Bo Wu, Guodong Sun
For the ore particle size detection, obtaining a sizable amount of high-quality ore labeled data is time-consuming and expensive.
1 code implementation • CVPR 2023 • Yun He, Danhang Tang, yinda zhang, xiangyang xue, Yanwei Fu
Most existing point cloud upsampling methods have roughly three steps: feature extraction, feature expansion and 3D coordinate prediction.
no code implementations • 26 Mar 2023 • Xuelin Qian, Yikai Wang, Yanwei Fu, Xinwei Sun, xiangyang xue, Jianfeng Feng
Our Latent Embedding Alignment (LEA) model concurrently recovers visual stimuli from fMRI signals and predicts brain activity from images within a unified framework.
no code implementations • 26 Mar 2023 • Simian Luo, Xuelin Qian, Yanwei Fu, yinda zhang, Ying Tai, Zhenyu Zhang, Chengjie Wang, xiangyang xue
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space.
1 code implementation • CVPR 2023 • Qiaole Dong, Chenjie Cao, Yanwei Fu
In this paper, we propose a rethinking to previous optical flow estimation.
no code implementations • 11 Mar 2023 • Chenjie Cao, Xinlin Ren, xiangyang xue, Yanwei Fu
To address these problems, we first apply one of the state-of-the-art learning-based MVS methods, --MVSFormer, to overcome intractable scenarios such as textureless and reflections regions suffered by traditional PatchMatch methods, but it fails in a few large scenes' reconstructions.
1 code implementation • Asian Conference on Computer Vision (ACCV) 2023 • Qizao Wang, Xuelin Qian, Yanwei Fu, xiangyang xue
In this paper, we first design a novel Shape Semantics Embedding (SSE) module to encode body shape semantic information, which is one of the essential clues to distinguish pedestrians when their clothes change.
Ranked #9 on
Person Re-Identification
on LTCC
1 code implementation • ICCV 2023 • Chenjie Cao, Yanwei Fu
Learning robust local image feature matching is a fundamental low-level vision task, which has been widely explored in the past few years.
1 code implementation • 22 Feb 2023 • Yikai Wang, Jianan Wang, Guansong Lu, Hang Xu, Zhenguo Li, Wei zhang, Yanwei Fu
In the image manipulation phase, SeMani adopts a generative model to synthesize new images conditioned on the entity-irrelevant regions and target text descriptions.
2 code implementations • CVPR 2023 • Yuqian Fu, Yu Xie, Yanwei Fu, Yu-Gang Jiang
Thus, inspired by vanilla adversarial learning, a novel model-agnostic meta Style Adversarial training (StyleAdv) method together with a novel style adversarial attack method is proposed for CD-FSL.
Ranked #1 on
Cross-Domain Few-Shot
on Plantae
1 code implementation • 6 Jan 2023 • Chengming Xu, Siqian Yang, Yabiao Wang, Zhanxiong Wang, Yanwei Fu, xiangyang xue
Essentially, despite ViTs have been shown to enjoy comparable or even better performance on other vision tasks, it is still very nontrivial to efficiently finetune the ViTs in real-world FSL scenarios.
1 code implementation • 3 Jan 2023 • Yanwei Fu, Xiaomei Wang, Hanze Dong, Yu-Gang Jiang, Meng Wang, xiangyang xue, Leonid Sigal
Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels.
1 code implementation • 2 Jan 2023 • Yikai Wang, Yanwei Fu, Xinwei Sun
While Knockoffs-SPR can be regarded as a sample selection module for a standard supervised training pipeline, we further combine it with a semi-supervised algorithm to exploit the support of noisy data as unlabeled data.
Ranked #1 on
Learning with noisy labels
on Clothing1M
no code implementations • ICCV 2023 • Simian Luo, Xuelin Qian, Yanwei Fu, yinda zhang, Ying Tai, Zhenyu Zhang, Chengjie Wang, xiangyang xue
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space.
no code implementations • CVPR 2023 • Xiang Li, Xuelin Qian, Litian Liang, Lingjie Kong, Qiaole Dong, Jiejun Chen, Dingxia Liu, Xiuzhong Yao, Yanwei Fu
Particularly, we build a causal graph, and train the images to estimate the intraoperative attributes for final OS prediction.
1 code implementation • 30 Nov 2022 • Chengming Xu, Chen Liu, Siqian Yang, Yabiao Wang, Shijie Zhang, Lijie Jia, Yanwei Fu
Since only part of the most confident positive samples are available and evidence is not enough to categorize the rest samples, many of these unlabeled data may also be the positive samples.
no code implementations • 29 Nov 2022 • Chengming Xu, Chen Liu, Xinwei Sun, Siqian Yang, Yabiao Wang, Chengjie Wang, Yanwei Fu
We theoretically show that such an augmentation mechanism, different from existing ones, is able to identify the causal features.
1 code implementation • 28 Nov 2022 • Qianyu Guo, Hongtong Gong, Xujun Wei, Yanwei Fu, Weifeng Ge, Yizhou Yu, Wenqiang Zhang
This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification.
1 code implementation • 23 Oct 2022 • Jian Yao, Yuxin Hong, Chiyu Wang, Tianjun Xiao, Tong He, Francesco Locatello, David Wipf, Yanwei Fu, Zheng Zhang
The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned.
2 code implementations • 12 Oct 2022 • Chenjie Cao, Qiaole Dong, Yanwei Fu
Specifically, given one corrupt image, we present the Transformer Structure Restorer (TSR) module to restore holistic structural priors at low image resolution, which are further upsampled by Simple Structure Upsampler (SSU) module to higher image resolution.
1 code implementation • 11 Oct 2022 • Yuqian Fu, Yu Xie, Yanwei Fu, Jingjing Chen, Yu-Gang Jiang
Concretely, to solve the data imbalance problem between the source data with sufficient examples and the auxiliary target data with limited examples, we build our model under the umbrella of multi-expert learning.
no code implementations • 7 Oct 2022 • Renjie Zhang, Yu Fang, Huaxin Song, Fangbin Wan, Yanwei Fu, Hirokazu Kato, Yang Wu
Cloth changing person re-identification(Re-ID) can work under more complicated scenarios with higher security than normal Re-ID and biometric techniques and is therefore extremely valuable in applications.
1 code implementation • 18 Aug 2022 • Boyan Jiang, Xinlin Ren, Mingsong Dou, xiangyang xue, Yanwei Fu, yinda zhang
Recent progress in 4D implicit representation focuses on globally controlling the shape and motion with low dimensional latent vectors, which is prone to missing surface details and accumulating tracking error.
1 code implementation • 4 Aug 2022 • Chenjie Cao, Xinlin Ren, Yanwei Fu
In this paper, we propose a pre-trained ViT enhanced MVS network called MVSFormer, which can learn more reliable feature representations benefited by informative priors from ViT.
Ranked #3 on
Point Clouds
on Tanks and Temples
1 code implementation • 3 Aug 2022 • Chenjie Cao, Qiaole Dong, Yanwei Fu
To this end, this paper incorporates the pre-training based Masked AutoEncoder (MAE) into the inpainting model, which enjoys richer informative priors to enhance the inpainting process.
3 code implementations • 19 Jul 2022 • Li Zhang, Jiachen Lu, Sixiao Zheng, Xinxuan Zhao, Xiatian Zhu, Yanwei Fu, Tao Xiang, Jianfeng Feng, Philip H. S. Torr
Extensive experiments show that our methods achieve appealing performance on a variety of dense prediction tasks (e. g., object detection and instance segmentation and semantic segmentation) as well as image classification.
no code implementations • 19 Jul 2022 • Shenghua Xu, Xinyue Cai, Bin Zhao, Li Zhang, Hang Xu, Yanwei Fu, xiangyang xue
This is because most of the existing lane detection methods either treat the lane detection as a dense prediction or a detection task, few of them consider the unique topologies (Y-shape, Fork-shape, nearly horizontal lane) of the lane markers, which leads to sub-optimal solution.
no code implementations • 17 Jul 2022 • Ke Fan, Yikai Wang, Qian Yu, Da Li, Yanwei Fu
In contrast, this paper proposes a simple Test-time Linear Training (ETLT) method for OOD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
1 code implementation • 17 Jun 2022 • Yifeng Zhuang, Qiang Sun, Yanwei Fu, Lifeng Chen, xiangyang xue
Since the attention mechanism in the transformer architecture can better integrate inter- and intra-modal information of vision and language.
no code implementations • 7 Jun 2022 • Chenjie Cao, Chengrong Wang, Yuntao Zhang, Yanwei Fu
Image inpainting is the task of filling masked or unknown regions of an image with visually realistic contents, which has been remarkably improved by Deep Neural Networks (DNNs) recently.
no code implementations • 9 May 2022 • Chilam Cheang, Haitao Lin, Yanwei Fu, xiangyang xue
This paper studies the task of any objects grasping from the known categories by free-form language instructions.
no code implementations • 9 May 2022 • Haitao Lin, Chilam Cheang, Yanwei Fu, xiangyang xue
The physical robot experiments confirm the utility of our method in object-cluttered scenes.
2 code implementations • CVPR 2022 • Fan Yan, Ming Nie, Xinyue Cai, Jianhua Han, Hang Xu, Zhen Yang, Chaoqiang Ye, Yanwei Fu, Michael Bi Mi, Li Zhang
We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space.
no code implementations • CVPR 2022 • Yun He, Xinlin Ren, Danhang Tang, yinda zhang, xiangyang xue, Yanwei Fu
To address this, we propose a novel deep point cloud compression method that preserves local density information.
no code implementations • 22 Apr 2022 • Satoshi Tsutsui, Yanwei Fu, David Crandall
One-shot fine-grained visual recognition often suffers from the problem of having few training examples for new fine-grained classes.
no code implementations • 21 Apr 2022 • Chao Wen, yinda zhang, Chenjie Cao, Zhuwen Li, xiangyang xue, Yanwei Fu
We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses.
1 code implementation • CVPR 2022 • Jianan Wang, Guansong Lu, Hang Xu, Zhenguo Li, Chunjing Xu, Yanwei Fu
Existing text-guided image manipulation methods aim to modify the appearance of the image or to edit a few objects in a virtual or simple scenario, which is far from practical application.
no code implementations • CVPR 2022 • Wenxuan Wang, Xuelin Qian, Yanwei Fu, xiangyang xue
With the wide applications of deep neural network models in various computer vision tasks, more and more works study the model vulnerability to adversarial examples.
no code implementations • 31 Mar 2022 • Xuelin Qian, Li Wang, Yi Zhu, Li Zhang, Yanwei Fu, xiangyang xue
Conventional 3D object detection approaches concentrate on bounding boxes representation learning with several parameters, i. e., localization, dimension, and orientation.
no code implementations • 28 Mar 2022 • Pan Li, Yanwei Fu, Shaogang Gong
The MFL computes meta-knowledge on functional regularisation generalisable to different learning tasks by which functional training on limited labelled data promotes more discriminative functions to be learned.
no code implementations • 27 Mar 2022 • Tianying Liu, Lu Zhang, Yang Wang, Jihong Guan, Yanwei Fu, Jiajia Zhao, Shuigeng Zhou
To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes.
no code implementations • 22 Mar 2022 • Yuxin Hong, Xuelin Qian, Simian Luo, xiangyang xue, Yanwei Fu
To this end, this paper proposes a novel model of learning to Quantize, Scrabble, and Craft (QS-Craft) for conditional human motion animation.
1 code implementation • CVPR 2022 • Yikai Wang, Xinwei Sun, Yanwei Fu
Noisy training set usually leads to the degradation of generalization and robustness of neural networks.
Ranked #4 on
Learning with noisy labels
on Clothing1M
1 code implementation • 15 Mar 2022 • Yuqian Fu, Yu Xie, Yanwei Fu, Jingjing Chen, Yu-Gang Jiang
The key challenge of CD-FSL lies in the huge data shift between source and target domains, which is typically in the form of totally different visual styles.
Ranked #3 on
Cross-Domain Few-Shot
on CUB
no code implementations • CVPR 2022 • Boyan Jiang, yinda zhang, Xingkui Wei, xiangyang xue, Yanwei Fu
A simple yet effective linear motion model is proposed to provide a rough and regularized motion estimation, followed by per-frame compensation for pose and geometry details with the residual encoded in the auxiliary code.
2 code implementations • CVPR 2022 • Qiaole Dong, Chenjie Cao, Yanwei Fu
The proposed model restores holistic image structures with a powerful attention-based transformer model in a fixed low-resolution sketch space.
1 code implementation • 20 Feb 2022 • Sixiao Zheng, Ke Fan, Yanxi Hou, Jianfeng Feng, Yanwei Fu
In contrast, the GPD fits the distribution of distance to the centroid exceeding a sufficiently large threshold, leading to a more stable performance of GPD k-means.
no code implementations • CVPR 2022 • Yu Xie, Yanwei Fu, Ying Tai, Yun Cao, Junwei Zhu, Chengjie Wang
In this paper, we propose a novel model to explicitly learn and memorize reusable features that can help hallucinate novel category images.
no code implementations • CVPR 2022 • Pan Li, Shaogang Gong, Chengjie Wang, Yanwei Fu
The calibrated distance in this target-aware non-linear subspace is complementary to that in the pre-trained representation.
no code implementations • 29 Sep 2021 • Wang Tian Xiang, Meiyue Shao, Yanwei Fu, Riheng Jia, Feilong Lin, ZhongLong Zheng
Typically, aggregation rules are utilized to protect the model from the attacks in federated learning.
no code implementations • 29 Sep 2021 • Yikai Wang, Xinwei Sun, Yanwei Fu
Specifically, we re-purpose a sparse linear model with incidental parameters as a unified Relative Instance Credibility Inference (RICI) framework, which will detect and remove outliers in the forward pass of each mini-batch and use the remaining instances to train the network.
no code implementations • 29 Sep 2021 • Chang Wan, Yanwei Fu, Ke Fan, Jinshan Zeng, Ming Zhong, Riheng Jia, MingLu Li, ZhongLong Zheng
However, the discriminator using logistic regression from the CFG framework is gradually hard to discriminate between real and fake images while the training steps go on.
no code implementations • 18 Sep 2021 • Yanwei Fu, Feng Li, Paula boned Fustel, Lei Zhao, Lijie Jia, Haojie Zheng, Qiang Sun, Shisong Rong, Haicheng Tang, xiangyang xue, Li Yang, Hong Li, Jiao Xie Wenxuan Wang, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian, Mengwei Gu
The image-level performance of COVID-19 prescreening model in the China-Spain multicenter study achieved an AUC of 0. 913 (95% CI, 0. 898-0. 927), with a sensitivity of 0. 695 (95% CI, 0. 643-0. 748), a specificity of 0. 904 (95% CI, 0. 891 -0. 919), an accuracy of 0. 875(0. 861-0. 889), and a F1 of 0. 611(0. 568-0. 655).
1 code implementation • ICCV 2021 • Xingkui Wei, Zhengqing Chen, Yanwei Fu, Zhaopeng Cui, yinda zhang
We present a deep learning pipeline that leverages network self-prior to recover a full 3D model consisting of both a triangular mesh and a texture map from the colored 3D point cloud.
no code implementations • 29 Jul 2021 • Fangrui Zhu, Yi Zhu, Li Zhang, Chongruo wu, Yanwei Fu, Mu Li
Semantic segmentation is a challenging problem due to difficulties in modeling context in complex scenes and class confusions along boundaries.
1 code implementation • 26 Jul 2021 • Yuqian Fu, Yanwei Fu, Yu-Gang Jiang
Secondly, a novel disentangle module together with a domain classifier is proposed to extract the disentangled domain-irrelevant and domain-specific features.
no code implementations • 25 Jul 2021 • Yuqian Fu, Yanwei Fu, Yu-Gang Jiang
To achieve this, a novel Mesh-based Video Action Imitation (M-VAI) method is proposed by us.
no code implementations • CVPR 2022 • Haitao Lin, Zichang Liu, Chilam Cheang, Yanwei Fu, Guodong Guo, xiangyang xue
The concatenation of the observed point cloud and symmetric one reconstructs a coarse object shape, thus facilitating object center (3D translation) and 3D size estimation.
no code implementations • 12 Jun 2021 • Yanwei Fu, Lei Zhao, Haojie Zheng, Qiang Sun, Li Yang, Hong Li, Jiao Xie, xiangyang xue, Feng Li, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian Mengwei Gu1
It is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts.
1 code implementation • NeurIPS 2021 • Chenjie Cao, Yuxin Hong, Xiang Li, Chengrong Wang, Chengming Xu, xiangyang xue, Yanwei Fu
To address these limitations, we propose a novel model -- image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis.
1 code implementation • 4 Jun 2021 • Zekun Luo, Zheng Fang, Sixiao Zheng, Yabiao Wang, Yanwei Fu
Non-Maximum Suppression (NMS) is essential for object detection and affects the evaluation results by incorporating False Positives (FP) and False Negatives (FN), especially in crowd occlusion scenes.
Ranked #6 on
Pedestrian Detection
on Caltech
no code implementations • CVPR 2021 • Wenxuan Wang, Bangjie Yin, Taiping Yao, Li Zhang, Yanwei Fu, Shouhong Ding, Jilin Li, Feiyue Huang, xiangyang xue
Previous substitute training approaches focus on stealing the knowledge of the target model based on real training data or synthetic data, without exploring what kind of data can further improve the transferability between the substitute and target models.
1 code implementation • CVPR 2021 • Li Wang, Liang Du, Xiaoqing Ye, Yanwei Fu, Guodong Guo, xiangyang xue, Jianfeng Feng, Li Zhang
The objective of this paper is to learn context- and depth-aware feature representation to solve the problem of monocular 3D object detection.
Ranked #14 on
Monocular 3D Object Detection
on KITTI Cars Moderate
1 code implementation • ICCV 2021 • Chenjie Cao, Yanwei Fu
To this end, this paper proposes learning a Sketch Tensor (ST) space for inpainting man-made scenes.
1 code implementation • CVPR 2021 • Chengming Xu, Chen Liu, Li Zhang, Chengjie Wang, Jilin Li, Feiyue Huang, xiangyang xue, Yanwei Fu
Our insight is that these methods would lead to poor adaptation with redundant matching, and leveraging channel-wise adjustment is the key to well adapting the learned knowledge to new classes.
1 code implementation • CVPR 2021 • Chuming Lin, Chengming Xu, Donghao Luo, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Yanwei Fu
Temporal action localization is an important yet challenging task in video understanding.
no code implementations • 23 Mar 2021 • Sixiao Zheng, Yanwei Fu, Yanxi Hou
However, zero-shot learning models assume that all seen classes should be known beforehand, while incremental learning models cannot recognize unseen classes.
no code implementations • CVPR 2021 • Boyan Jiang, yinda zhang, Xingkui Wei, xiangyang xue, Yanwei Fu
To model the motion, a neural Ordinary Differential Equation (ODE) is trained to update the initial state conditioned on the learned motion code, and a decoder takes the shape code and the updated state code to reconstruct the 3D model at each time stamp.
no code implementations • ICCV 2021 • Pan Li, Da Li, Wei Li, Shaogang Gong, Yanwei Fu, Timothy M. Hospedales
The topical domain generalization (DG) problem asks trained models to perform well on an unseen target domain with different data statistics from the source training domains.
5 code implementations • CVPR 2021 • Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip H. S. Torr, Li Zhang
In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task.
Ranked #2 on
Semantic Segmentation
on FoodSeg103
(using extra training data)
no code implementations • 17 Nov 2020 • Satoshi Tsutsui, Yanwei Fu, David Crandall
But while one's own face is not frequently visible, their hands are: in fact, hands are among the most common objects in one's own field of view.
1 code implementation • 15 Nov 2020 • Jianan Wang, Boyang Li, Xiangyu Fan, Jing Lin, Yanwei Fu
The task of video and text sequence alignment is a prerequisite step toward joint understanding of movie videos and screenplays.
1 code implementation • 20 Oct 2020 • Yuqian Fu, Li Zhang, Junke Wang, Yanwei Fu, Yu-Gang Jiang
Humans can easily recognize actions with only a few examples given, while the existing video recognition models still heavily rely on the large-scale labeled data inputs.
Ranked #2 on
Few Shot Action Recognition
on Kinetics-100
no code implementations • 7 Oct 2020 • Xuelin Qian, Huazhu Fu, Weiya Shi, Tao Chen, Yanwei Fu, Fei Shan, xiangyang xue
To counter the outbreak of COVID-19, the accurate diagnosis of suspected cases plays a crucial role in timely quarantine, medical treatment, and preventing the spread of the pandemic.
no code implementations • 4 Sep 2020 • Yanwei Fu, Feng Li, Wenxuan Wang, Haicheng Tang, Xuelin Qian, Mengwei Gu, xiangyang xue
After more than four months study, we found that the confirmed cases of COVID-19 present the consistent ocular pathological symbols; and we propose a new screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras, could reliably make a rapid risk screening of COVID-19 with very high accuracy.
1 code implementation • ECCV 2020 • Jinlong Peng, Changan Wang, Fangbin Wan, Yang Wu, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Yanwei Fu
Existing Multiple-Object Tracking (MOT) methods either follow the tracking-by-detection paradigm to conduct object detection, feature extraction and data association separately, or have two of the three subtasks integrated to form a partially end-to-end solution.
2 code implementations • 15 Jul 2020 • Yikai Wang, Li Zhang, Yuan YAO, Yanwei Fu
We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances.
1 code implementation • 4 Jul 2020 • Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan YAO
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.
no code implementations • 22 Jun 2020 • Fangrui Zhu, Li Zhang, Yanwei Fu, Guodong Guo, Weidi Xie
The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a. k. a.
no code implementations • 26 May 2020 • Xuelin Qian, Wenxuan Wang, Li Zhang, Fangrui Zhu, Yanwei Fu, Tao Xiang, Yu-Gang Jiang, xiangyang xue
Specifically, we consider that under cloth-changes, soft-biometrics such as body shape would be more reliable.
1 code implementation • CVPR 2020 • Hangyu Lin, Yanwei Fu, Yu-Gang Jiang, xiangyang xue
Unfortunately, the representation learned by SketchRNN is primarily for the generation tasks, rather than the other tasks of recognition and retrieval of sketches.
1 code implementation • CVPR 2020 • Yikai Wang, Chengming Xu, Chen Liu, Li Zhang, Yanwei Fu
To measure the credibility of each pseudo-labeled instance, we then propose to solve another linear regression hypothesis by increasing the sparsity of the incidental parameters and rank the pseudo-labeled instances with their sparsity degree.
1 code implementation • CVPR 2020 • Jiashun Wang, Chao Wen, Yanwei Fu, Haitao Lin, Tianyun Zou, xiangyang xue, yinda zhang
Pose transfer has been studied for decades, in which the pose of a source mesh is applied to a target mesh.
no code implementations • 9 Mar 2020 • Fangbin Wan, Yang Wu, Xuelin Qian, Yixiong Chen, Yanwei Fu
We find that changing clothes makes ReID a much harder problem in the sense of bringing difficulties to learning effective representations and also challenges the generalization ability of previous ReID models to identify persons with unseen (new) clothes.