FastReID: A Pytorch Toolbox for General Instance Re-identification

He, Lingxiao; Liao, Xingyu; Liu, Wu; Liu, Xinchen; Cheng, Peng; Mei, Tao

doi:10.48550/arxiv.2006.02631

Cited by 57 publications

(74 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We render images by Blender Python Library [1]. In the training stage, We use the Fastreid [14], a toolkit based on PyTorch [25], as the basic training framework. We use ResNet-50 [13] structure as the backbone, which is pretrained on ImageNet [7].…”

Section: Implementation Detailsmentioning

confidence: 99%

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

Chen¹,

He²,

Du³

et al. 2021

Preprint

View full text Add to dashboard Cite

Nowadays, real data in person re-identification (ReID) task is facing privacy issues, e.g., the banned dataset DukeMTMC-ReID. Thus it becomes much harder to collect real data for ReID task. Meanwhile, the labor cost of labeling ReID data is still very high and further hinders the development of the ReID research. Therefore, many methods turn to generate synthetic images for ReID algorithms as alternatives instead of real images. However, there is an inevitable domain gap between synthetic and real images. In previous methods, the generation process is based on virtual scenes, and their synthetic training data can not be changed according to different target real scenes automatically. To handle this problem, we propose a novel Target-Aware Generation pipeline to produce synthetic person images, called TAGPerson. Specifically, it involves a parameterized rendering method, where the parameters are controllable and can be adjusted according to target scenes. In TAGPerson, we extract information from target scenes and use them to control our parameterized rendering process to generate target-aware synthetic images, which would hold a smaller gap to the real images in the target domain. In our experiments, our target-aware synthetic images can achieve a much higher performance than the generalized synthetic images on MSMT17, i.e. 47.5% vs. 40.9% for rank-1 accuracy. We will release this toolkit 1 for the ReID community to generate synthetic images at any desired taste.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

Chen¹,

He²,

Du³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We use the PyTorch toolbox, FastReID [22], to achieve the proposed LDS. Additionally, we use the ResNet-ibn [20] [42] as our backbone and initialize it by the ImageNet [11] pre-trained model.…”

Section: Implementation Detailsmentioning

confidence: 99%

Learning to Disentangle Scenes for Person Re-identification

Zang,

Li,

Gao

et al. 2021

Preprint

View full text Add to dashboard Cite

There are many challenging problems in the person re-identification (ReID) task, such as the occlusion and scale variation. Existing works usually tried to solve them by employing a one-branch network. This one-branch network needs to be robust to various challenging problems, which makes this network overburdened. This paper proposes to divide-and-conquer the ReID task. For this purpose, we employ several self-supervision operations to simulate different challenging problems and handle each challenging problem using different networks. Concretely, we use the random erasing operation and propose a novel random scaling operation to generate new images with controllable characteristics. A general multi-branch network, including one master branch and two servant branches, is introduced to handle different scenes. These branches learn collaboratively and achieve different perceptive abilities. In this way, the complex scenes in the ReID task are effectively disentangled, and the burden of each branch is relieved. The results from extensive experiments demonstrate that the proposed method achieves state-of-the-art performances on three ReID benchmarks and two occluded ReID benchmarks. Ablation study also shows that the proposed scheme and operations significantly improve the performance in various scenes.

show abstract

“…In addition, the experimental results show that the JAD is applicable to other baselines performs well. Where Strong Baseline (SB) [27] is implemented based on the Resnet50 backbone network adding the Batch Normalization Neck structure, and FastReID (FR) [28] is implemented based on the IBN-ResNet101 [29] backbone network. All in all, the method proposed in this paper has good defense effect in both white-box attack and black-box attack.…”

Section: Experiments Of Jadmentioning

confidence: 99%

Robust Person Re-identification with Multi-Modal Joint Defence

Gong¹,

Huang²,

Chen³

2021

Preprint

View full text Add to dashboard Cite

The Person Re-identification (ReID) system based on metric learning has been proved to inherit the vulnerability of deep neural networks (DNNs), which are easy to be fooled by adversarail metric attacks. Existing work mainly relies on adversarial training for metric defense, and more methods have not been fully studied. By exploring the impact of attacks on the underlying features, we propose targeted methods for metric attacks and defence methods. In terms of metric attack, we use the local color deviation to construct the intra-class variation of the input to attack color features. In terms of metric defenses, we propose a joint defense method which includes two parts of proactive defense and passive defense. Proactive defense helps to enhance the robustness of the model to color variations and the learning of structure relations across multiple modalities by constructing different inputs from multimodal images, and passive defense exploits the invariance of structural features in a changing pixel space by circuitous scaling to preserve structural features while eliminating some of the adversarial noise. Extensive experiments demonstrate that the proposed joint defense compared with the existing adversarial metric defense methods which not only against multiple attacks at the same time but also has not significantly reduced the generalization capacity of the model.

show abstract

FastReID: A Pytorch Toolbox for General Instance Re-identification

Cited by 57 publications

References 50 publications

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

Learning to Disentangle Scenes for Person Re-identification

Robust Person Re-identification with Multi-Modal Joint Defence

Contact Info

Product

Resources

About