2 code implementations • 21 Mar 2024 • Quan Zhang, Lei Wang, Vishal M. Patel, Xiaohua Xie, JianHuang Lai
Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5. 0%/2. 7% on CARGO and 3. 7%/5. 2% on AG-ReID, keeping the same magnitude of computational complexity.
Ranked #1 on Person Re-Identification on AG-ReID
1 code implementation • 13 Mar 2024 • Pengze Zhang, Hubery Yin, Chen Li, Xiaohua Xie
Most diffusion models assume that the reverse process adheres to a Gaussian distribution.
1 code implementation • 28 Feb 2024 • Yanzuo Lu, Manlin Zhang, Andy J Ma, Xiaohua Xie, Jian-Huang Lai
While existing methods simply align the person appearance to the target pose, they are prone to overfitting due to the lack of a high-level semantic understanding on the source person image.
no code implementations • 13 Jan 2024 • Junxi Chen, Junhao Dong, Xiaohua Xie
Recently, many studies utilized adversarial examples (AEs) to raise the cost of malicious image editing and copyright violation powered by latent diffusion models (LDMs).
no code implementations • 29 Dec 2023 • Yun Chen, Lingxiao Yang, Qi Chen, Jian-Huang Lai, Xiaohua Xie
We introduce a two-stage pipeline to effectively train our network: Stage I utilizes inter-speech contrastive learning to model fine-grained emotion and intra-speech disentanglement learning to better separate emotion and content.
1 code implementation • 13 Dec 2023 • Yanzuo Lu, Meng Shen, Andy J Ma, Xiaohua Xie, Jian-Huang Lai
Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer.
Ranked #2 on Universal Domain Adaptation on Office-Home
1 code implementation • ICCV 2023 • Shenghao Fu, Junkai Yan, Yipeng Gao, Xiaohua Xie, Wei-Shi Zheng
We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors.
no code implementations • 11 Jul 2023 • Zixuan Chen, Lingxiao Yang, JianHuang Lai, Xiaohua Xie
However, these methods have not considered the correlation between adjacent projection views, resulting in aliasing artifacts on SV sinograms.
no code implementations • 16 May 2023 • Junxi Chen, Junhao Dong, Xiaohua Xie
However, a recent work showed the inequality phenomena in $l_{\infty}$-adversarial training and revealed that the $l_{\infty}$-adversarially trained model is vulnerable when a few important pixels are perturbed by i. i. d.
no code implementations • 28 Mar 2023 • Zixuan Chen, Xiaohua Xie, Lingxiao Yang, JianHuang Lai
Additionally, to meet the speed-accuracy demands, we further propose \textbf{P}ixel-level \textbf{T}emplate \textbf{S}election (PTS) to streamline the original template set.
Ranked #13 on Anomaly Detection on MVTec LOCO AD
1 code implementation • ICCV 2023 • Zixuan Chen, Jian-Huang Lai, Lingxiao Yang, Xiaohua Xie
Medical image arbitrary-scale super-resolution (MIASSR) has recently gained widespread attention, aiming to super sample medical volumes at arbitrary scales via a single model.
no code implementations • 24 Mar 2023 • Junhao Dong, Junxi Chen, Xiaohua Xie, JianHuang Lai, Hao Chen
In this exposition, we present a comprehensive survey on recent advances in adversarial attack and defense for medical image analysis with a novel taxonomy in terms of the application scenario.
no code implementations • CVPR 2023 • Junhao Dong, Seyed-Mohsen Moosavi-Dezfooli, JianHuang Lai, Xiaohua Xie
To circumvent this issue, we propose a novel adversarial training scheme that encourages the model to produce similar outputs for an adversarial example and its ``inverse adversarial'' counterpart.
2 code implementations • Proceedings of Machine Learning Research 2022 • Lingxiao Yang, Ru-Yuan Zhang, Lida Li, Xiaohua Xie
Another advantage of the module is that most of the operators are selected based on the solution to the defined energy function, avoiding too many efforts for structure tuning.
1 code implementation • CVPR 2023 • Huajun Zhou, Bo Qiao, Lingxiao Yang, JianHuang Lai, Xiaohua Xie
In this paper, we propose a novel USOD method to mine rich and accurate saliency knowledge from both easy and hard samples.
1 code implementation • 19 Jun 2022 • Jianxiong Tang, JianHuang Lai, Xiaohua Xie, Lingxiao Yang, Wei-Shi Zheng
The SNN2ANN consists of 2 components: a) a weight sharing architecture between ANN and SNN and b) spiking mapping units.
no code implementations • 18 May 2022 • Jiahao Zhu, Huajun Zhou, Zixuan Chen, Yi Zhou, Xiaohua Xie
3D deep models consuming point clouds have achieved sound application effects in computer vision.
1 code implementation • 27 Apr 2022 • Xin Zhang, Xiaohua Xie, JianHuang Lai, Wei-Shi Zheng
To address this issue, we propose a pedestrian retrieval framework based on cross-camera trajectory generation, which integrates both temporal and spatial information.
no code implementations • 26 Apr 2022 • Junhao Dong, YuAn Wang, JianHuang Lai, Xiaohua Xie
DeepFake face swapping presents a significant threat to online security and social media, which can replace the source face in an arbitrary photo/video with the target face of an entirely different person.
1 code implementation • CVPR 2022 • Pengze Zhang, Lingxiao Yang, JianHuang Lai, Xiaohua Xie
Pose Guided Person Image Generation (PGPIG) is the task of transforming a person image from the source pose to a given target pose.
1 code implementation • CVPR 2022 • Qi Chen, Lingxiao Yang, JianHuang Lai, Xiaohua Xie
Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has attracted much attention due to low annotation costs.
Ranked #20 on Weakly-Supervised Semantic Segmentation on COCO 2014 val
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
1 code implementation • 7 Feb 2022 • Huajun Zhou, Yang Lin, Lingxiao Yang, JianHuang Lai, Xiaohua Xie
In recent years, deep network-based methods have continuously refreshed state-of-the-art performance on Salient Object Detection (SOD) task.
no code implementations • CVPR 2022 • Junhao Dong, YuAn Wang, Jian-Huang Lai, Xiaohua Xie
Extensive experiments show that our method can significantly outperform state-of-the-art adversarially robust FSIC methods on two standard benchmarks.
1 code implementation • CVPR 2022 • Quan Zhang, Kaiheng Dang, Jian-Huang Lai, Zhanxiang Feng, Xiaohua Xie
To the best of our knowledge, 3DT is the first work to address GReID with 3D perspective, and the City1M is the currently largest dataset.
1 code implementation • 7 Dec 2021 • Huajun Zhou, Peijia Chen, Lingxiao Yang, JianHuang Lai, Xiaohua Xie
Moreover, a new loss function is proposed to facilitate the generation of high-quality pseudo labels.
no code implementations • 18 Sep 2021 • Yuedong Chen, Junjia Huang, JianFeng Wang, Xiaohua Xie
Motion deblurring has witnessed rapid development in recent years, and most of the recent methods address it by using deep learning techniques, with the help of different kinds of prior knowledge.
no code implementations • 21 Oct 2019 • Jiabo Huang, Xiaohua Xie, Wei-Shi Zheng
This paper studies the problem of aligning a set of face images of the same individual into a normalized image while removing the outliers like partial occlusion, extreme facial expression as well as significant illumination variation.
no code implementations • 6 Aug 2019 • Zixuan Chen, Huajun Zhou, Xiaohua Xie, Jian-Huang Lai
Yet the Contour Loss emphasizes on the local saliency.
1 code implementation • 29 Jan 2019 • Guangcong Wang, Jian-Huang Lai, Zhenyu Xie, Xiaohua Xie
With the discovered underlying person structure, the RLD method builds a bridge between the global and local feature representation and thus improves the capacity of feature representation for person re-ID.
3 code implementations • 8 Dec 2018 • Guangcong Wang, Jian-Huang Lai, Peigen Huang, Xiaohua Xie
In this paper, we propose a novel two-stream spatial-temporal person ReID (st-ReID) framework that mines both visual semantic information and spatial-temporal information.
Ranked #4 on Person Re-Identification on Market-1501
no code implementations • 30 Mar 2018 • Zhanxiang Feng, Jian-Huang Lai, Xiaohua Xie
In recent years, a growing body of research has focused on the problem of person re-identification (re-id).
no code implementations • ICCV 2017 • Guangcong Wang, Xiaohua Xie, Jian-Huang Lai, Jiaxuan Zhuo
A bottleneck of SSL is the overfitting problem when training over the limited labeled data, especially on a complex model like a deep neural network.
no code implementations • 25 Jul 2017 • Chunchao Guo, Jian-Huang Lai, Xiaohua Xie
We present a novel method of integrating motion and appearance cues for foreground object segmentation in unconstrained videos.