Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimization

• URL: http://arxiv.org/abs/2404.12611v1
• Date: Fri, 19 Apr 2024 03:45:12 GMT
• Title: Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimization
• Authors: Junjie Li, Guanshuo Wang, Fufu Yu, Yichao Yan, Qiong Jia, Shouhong Ding, Xingdong Sheng, Yunhui Liu, Xiaokang Yang,
• Abstract summary: Clothes-changing person re-identification (CC-ReID) aims to retrieve images of the same person wearing different outfits. The same-clothes discrimination as the standard ReID learning objective in CC-ReID is persistently ignored in previous researches. In this study, we dive into the relationship between standard and clothes-changing(CC) learning objectives, and bring the inner conflicts between these two objectives to the fore.
• Score: 90.41318757397097
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Clothes-changing person re-identification (CC-ReID) aims to retrieve images of the same person wearing different outfits. Mainstream researches focus on designing advanced model structures and strategies to capture identity information independent of clothing. However, the same-clothes discrimination as the standard ReID learning objective in CC-ReID is persistently ignored in previous researches. In this study, we dive into the relationship between standard and clothes-changing~(CC) learning objectives, and bring the inner conflicts between these two objectives to the fore. We try to magnify the proportion of CC training pairs by supplementing high-fidelity clothes-varying synthesis, produced by our proposed Clothes-Changing Diffusion model. By incorporating the synthetic images into CC-ReID model training, we observe a significant improvement under CC protocol. However, such improvement sacrifices the performance under the standard protocol, caused by the inner conflict between standard and CC. For conflict mitigation, we decouple these objectives and re-formulate CC-ReID learning as a multi-objective optimization (MOO) problem. By effectively regularizing the gradient curvature across multiple objectives and introducing preference restrictions, our MOO solution surpasses the single-task training paradigm. Our framework is model-agnostic, and demonstrates superior performance under both CC and standard ReID protocols.

Related papers

• On Feature Decorrelation in Cloth-Changing Person Re-identification [32.27835236681253]
  Cloth-changing person re-identification (CC-ReID) poses a significant challenge in computer vision. Traditional methods to achieve this involve integrating multi-modality data or employing manually annotated clothing labels. We introduce a novel regularization technique based on density ratio estimation.
  arXiv  Detail & Related papers  (2024-10-07T22:25:37Z)
• Content and Salient Semantics Collaboration for Cloth-Changing Person Re-Identification [74.10897798660314]
  Cloth-changing person Re-IDentification aims at recognizing the same person with clothing changes across non-overlapping cameras. We propose the Content and Salient Semantics Collaboration framework, facilitating cross-parallel semantics interaction and refinement. Our framework is simple yet effective, and the vital design is the Semantics Mining and Refinement (SMR) module.
  arXiv  Detail & Related papers  (2024-05-26T15:17:28Z)
• Identity-aware Dual-constraint Network for Cloth-Changing Person Re-identification [13.709863134725335]
  Cloth-Changing Person Re-Identification (CC-ReID) aims to accurately identify the target person in more realistic surveillance scenarios, where pedestrians usually change their clothing. Despite great progress, limited cloth-changing training samples in existing CC-ReID datasets still prevent the model from adequately learning cloth-irrelevant features. We propose an Identity-aware Dual-constraint Network (IDNet) for the CC-ReID task.
  arXiv  Detail & Related papers  (2024-03-13T05:46:36Z)
• Semantic-aware Consistency Network for Cloth-changing Person Re-Identification [8.885551377703944]
  We present a Semantic-aware Consistency Network (SCNet) to learn identity-related semantic features. We generate the black-clothing image by erasing pixels in the clothing area. We further design a semantic consistency loss to facilitate the learning of high-level identity-related semantic features.
  arXiv  Detail & Related papers  (2023-08-27T14:07:57Z)
• Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification [118.23912884472794]
  Clothes-invariant feature extraction is critical to the clothes-changing person re-identification (CC-ReID) We argue that there exists a strong spurious correlation between clothes and human identity, that restricts the common likelihood-based ReID method P(Y|X) to extract clothes-irrelevant features. We propose a new Causal Clothes-Invariant Learning (CCIL) method to achieve clothes-invariant feature learning.
  arXiv  Detail & Related papers  (2023-05-10T13:48:24Z)
• Switchable Representation Learning Framework with Self-compatibility [50.48336074436792]
  We propose a Switchable representation learning Framework with Self-Compatibility (SFSC) SFSC generates a series of compatible sub-models with different capacities through one training process. SFSC achieves state-of-the-art performance on the evaluated datasets.
  arXiv  Detail & Related papers  (2022-06-16T16:46:32Z)
• ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension [114.85628613911713]
  Large-scale pre-trained models are useful for image classification across domains. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC.
  arXiv  Detail & Related papers  (2022-04-12T17:55:38Z)
• Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering [30.17063272667769]
  This paper proposes a novel framework, named ConCF, that exploits the complementarity from heterogeneous objectives throughout the training process. Our experiments on real-world datasets demonstrate that ConCF significantly improves the generalization of the model.
  arXiv  Detail & Related papers  (2022-02-26T13:34:29Z)
• Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization [65.50321170655225]
  We introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations. Experiments on image-based Cloth-Changing ReID benchmarks, e.g., LTCC, PRCC, Real28, and VC-Clothes, demonstrate that GI-ReID performs favorably against the state-of-the-arts.
  arXiv  Detail & Related papers  (2021-03-29T12:10:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.