ReMix: Training Generalized Person Re-identification on a Mixture of Data

• URL: http://arxiv.org/abs/2410.21938v1
• Date: Tue, 29 Oct 2024 10:57:03 GMT
• Title: ReMix: Training Generalized Person Re-identification on a Mixture of Data
• Abstract summary: ReMix is a generalized Re-ID method jointly trained on a mixture of limited labeled multi-camera and large unlabeled single-camera data. Experiments show that ReMix has a high generalization ability and outperforms state-of-the-art methods in generalizable person Re-ID.
• Score: 1.77513002450736
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Modern person re-identification (Re-ID) methods have a weak generalization ability and experience a major accuracy drop when capturing environments change. This is because existing multi-camera Re-ID datasets are limited in size and diversity, since such data is difficult to obtain. At the same time, enormous volumes of unlabeled single-camera records are available. Such data can be easily collected, and therefore, it is more diverse. Currently, single-camera data is used only for self-supervised pre-training of Re-ID methods. However, the diversity of single-camera data is suppressed by fine-tuning on limited multi-camera data after pre-training. In this paper, we propose ReMix, a generalized Re-ID method jointly trained on a mixture of limited labeled multi-camera and large unlabeled single-camera data. Effective training of our method is achieved through a novel data sampling strategy and new loss functions that are adapted for joint use with both types of data. Experiments show that ReMix has a high generalization ability and outperforms state-of-the-art methods in generalizable person Re-ID. To the best of our knowledge, this is the first work that explores joint training on a mixture of multi-camera and single-camera data in person Re-ID.

Related papers

• ReText: Text Boosts Generalization in Image-Based Person Re-identification [5.637102825156504]
  Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining.<n>We propose ReText, a novel method trained on a mixture of multi-camera and single-camera data.
  arXiv  Detail & Related papers  (2026-02-05T15:43:31Z)
• DynaMix: Generalizable Person Re-identification via Dynamic Relabeling and Mixed Data Sampling [5.977582457028636]
  Generalizable person re-identification (Re-ID) aims to recognize individuals across unseen cameras and environments.<n>We propose DynaMix, a novel method that effectively combines manually labeled multi-camera and large-scale pseudo-labeled single-camera data.<n>We show that DynaMix consistently outperforms state-of-the-art methods in generalizable person Re-ID.
  arXiv  Detail & Related papers  (2025-11-24T13:01:32Z)
• Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training [51.87027943520492]
  We present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities. Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities.
  arXiv  Detail & Related papers  (2024-06-10T06:26:03Z)
• Learning Intra and Inter-Camera Invariance for Isolated Camera Supervised Person Re-identification [6.477096324232456]
  Cross-camera images are prone to being recognized as different IDs simply by camera style. This paper studies person re-ID under such isolated camera supervised (ISCS) setting.
  arXiv  Detail & Related papers  (2023-11-02T11:32:40Z)
• Handling Label Uncertainty for Camera Incremental Person Re-Identification [17.5026399908583]
  Incremental learning for person re-identification (ReID) aims to develop models that can be trained with a continuous data stream. New data collected from new cameras may probably contain an unknown proportion of identities seen before. We propose a novel framework ExtendOVA to handle the class overlap issue.
  arXiv  Detail & Related papers  (2022-10-17T02:59:54Z)
• Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification [60.36551512902312]
  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.
  arXiv  Detail & Related papers  (2021-03-08T09:13:06Z)
• 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)
• Unsupervised Pre-training for Person Re-identification [90.98552221699508]
  We present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" We make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation.
  arXiv  Detail & Related papers  (2020-12-07T14:48:26Z)
• Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning [41.115022307850424]
  We develop an efficient model adaptation approach using hypothesis transfer learning for person re-identification. Our approach minimizes the effect of negative transfer by finding an optimal weighted combination of multiple source models for transferring the knowledge.
  arXiv  Detail & Related papers  (2020-07-22T00:43:29Z)
• Intra-Camera Supervised Person Re-Identification [87.88852321309433]
  We propose a novel person re-identification paradigm based on an idea of independent per-camera identity annotation. This eliminates the most time-consuming and tedious inter-camera identity labelling process. We formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method for Intra-Camera Supervised (ICS) person re-id.
  arXiv  Detail & Related papers  (2020-02-12T15:26:33Z)
• Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization [90.9485099181197]
  This paper rethinks the working mechanism of conventional ReID approaches. We force the image data of all cameras to fall onto the same subspace, so that the distribution gap between any camera pair is largely shrunk. Experiments on a wide range of ReID tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-01-23T17:22:34Z)

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.