Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification

• URL: http://arxiv.org/abs/2103.04618v1
• Date: Mon, 8 Mar 2021 09:13:06 GMT
• Title: Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
• Authors: Fengxiang Yang, Zhun Zhong, Zhiming Luo, Yuanzheng Cai, Yaojin Lin, Shaozi Li, Nicu Sebe
• Abstract summary: unsupervised person re-identification (re-ID) aims to learn discriminative models with unlabeled data. One popular method is to obtain pseudo-label by clustering and use them to optimize the model. In this paper, we propose a unified framework to solve both problems.
• Score: 60.36551512902312
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data. One popular method is to obtain pseudo-label by clustering and use them to optimize the model. Although this kind of approach has shown promising accuracy, it is hampered by 1) noisy labels produced by clustering and 2) feature variations caused by camera shift. The former will lead to incorrect optimization and thus hinders the model accuracy. The latter will result in assigning the intra-class samples of different cameras to different pseudo-label, making the model sensitive to camera variations. In this paper, we propose a unified framework to solve both problems. Concretely, we propose a Dynamic and Symmetric Cross-Entropy loss (DSCE) to deal with noisy samples and a camera-aware meta-learning algorithm (MetaCam) to adapt camera shift. DSCE can alleviate the negative effects of noisy samples and accommodate the change of clusters after each clustering step. MetaCam simulates cross-camera constraint by splitting the training data into meta-train and meta-test based on camera IDs. With the interacted gradient from meta-train and meta-test, the model is enforced to learn camera-invariant features. Extensive experiments on three re-ID benchmarks show the effectiveness and the complementary of the proposed DSCE and MetaCam. Our method outperforms the state-of-the-art methods on both fully unsupervised re-ID and unsupervised domain adaptive re-ID.

Related papers

• Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification [21.831927539161413]
  Single-camera-training person re-identification (SCT re-ID) aims to train a re-ID model using SCT datasets where each person appears in only one camera. Main challenge of SCT re-ID is to learn camera-invariant feature representations without cross-camera same-person (CCSP) data as supervision. We propose a Camera-Invariant Meta-Learning Network (CIMN) for SCT re-ID.
  arXiv  Detail & Related papers  (2024-06-21T00:15:32Z)
• Camera-aware Label Refinement for Unsupervised Person Re-identification [19.099192313056296]
  Unsupervised person re-identification aims to retrieve images of a specified person without identity labels. Recent unsupervised Re-ID approaches adopt clustering-based methods to measure cross-camera feature similarity. We introduce a textbfCamera-textbfAware textbfLabel textbfRefinement(CALR) framework that reduces camera discrepancy by clustering intra-camera similarity.
  arXiv  Detail & Related papers  (2024-03-25T06:22:27Z)
• Domain-adaptive Person Re-identification without Cross-camera Paired Samples [12.041823465553875]
  Cross-camera pedestrian samples collected from long-distance scenes often have no positive samples. It is extremely challenging to use cross-camera negative samples to achieve cross-region pedestrian identity matching. A novel domain-adaptive person re-ID method that focuses on cross-camera consistent discriminative feature learning is proposed.
  arXiv  Detail & Related papers  (2023-07-13T02:42:28Z)
• Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection [64.65563422852568]
  We improve the challenging monocular 3D object detection problem with a general semi-supervised framework. We introduce a novel, simple, yet effective Augment and Criticize' framework that explores abundant informative samples from unlabeled data. The two new detectors, dubbed 3DSeMo_DLE and 3DSeMo_FLEX, achieve state-of-the-art results with remarkable improvements for over 3.5% AP_3D/BEV (Easy) on KITTI.
  arXiv  Detail & Related papers  (2023-03-20T16:28:15Z)
• Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID [17.90248359024435]
  Systems for person re-identification (ReID) can achieve a high accuracy when trained on large fully-labeled image datasets. The domain shift associated with diverse operational capture conditions (e.g., camera viewpoints and lighting) may translate to a significant decline in performance. This paper focuses on unsupervised domain adaptation (UDA) for video-based ReID.
  arXiv  Detail & Related papers  (2022-11-07T15:32:56Z)
• Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes [70.30052164401178]
  Person re-identification (Re-ID) aims to match person images across non-overlapping camera views. ICS-DS Re-ID uses cross-camera unpaired data with intra-camera identity labels for training. Cross-camera feature prediction method to mine cross-camera self supervision information. Joint learning of global-level and local-level features forms a global-local cross-camera feature prediction scheme.
  arXiv  Detail & Related papers  (2021-07-29T11:27:50Z)
• Intra-Inter Camera Similarity for Unsupervised Person Re-Identification [50.85048976506701]
  We study a novel intra-inter camera similarity for pseudo-label generation. We train our re-id model in two stages with intra-camera and inter-camera pseudo-labels, respectively. This simple intra-inter camera similarity produces surprisingly good performance on multiple datasets.
  arXiv  Detail & Related papers  (2021-03-22T08:29:04Z)
• Camera-aware Proxies for Unsupervised Person Re-Identification [60.26031011794513]
  This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations. We propose to split each single cluster into multiple proxies and each proxy represents the instances coming from the same camera. Based on the camera-aware proxies, we design both intra- and inter-camera contrastive learning components for our Re-ID model.
  arXiv  Detail & Related papers  (2020-12-19T12:37:04Z)
• Towards Precise Intra-camera Supervised Person Re-identification [54.86892428155225]
  Intra-camera supervision (ICS) for person re-identification (Re-ID) assumes that identity labels are independently annotated within each camera view. Lack of inter-camera labels makes the ICS Re-ID problem much more challenging than the fully supervised counterpart. Our approach performs even comparable to state-of-the-art fully supervised methods in two of the datasets.
  arXiv  Detail & Related papers  (2020-02-12T11:56:30Z)

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.