Bi-C2R: Bidirectional Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification

• URL: http://arxiv.org/abs/2512.25000v1
• Date: Wed, 31 Dec 2025 17:50:05 GMT
• Title: Bi-C2R: Bidirectional Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
• Authors: Zhenyu Cui, Jiahuan Zhou, Yuxin Peng,
• Abstract summary: Lifelong person Re-IDentification (L-ReID) exploits sequentially collected data to continuously train and update a ReID model.<n>Existing L-ReID methods typically re-extract new features for all historical gallery images for inference after each update, known as "re-indexing"<n>This paper focuses on a new task called Re-index Free Lifelong person Re-IDentification (RFL-ReID), which requires performing lifelong person re-identification without re-indexing historical gallery images.
• Score: 77.07028925223383
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lifelong person Re-IDentification (L-ReID) exploits sequentially collected data to continuously train and update a ReID model, focusing on the overall performance of all data. Its main challenge is to avoid the catastrophic forgetting problem of old knowledge while training on new data. Existing L-ReID methods typically re-extract new features for all historical gallery images for inference after each update, known as "re-indexing". However, historical gallery data typically suffers from direct saving due to the data privacy issue and the high re-indexing costs for large-scale gallery images. As a result, it inevitably leads to incompatible retrieval between query features extracted by the updated model and gallery features extracted by those before the update, greatly impairing the re-identification performance. To tackle the above issue, this paper focuses on a new task called Re-index Free Lifelong person Re-IDentification (RFL-ReID), which requires performing lifelong person re-identification without re-indexing historical gallery images. Therefore, RFL-ReID is more challenging than L-ReID, requiring continuous learning and balancing new and old knowledge in diverse streaming data, and making the features output by the new and old models compatible with each other. To this end, we propose a Bidirectional Continuous Compatible Representation (Bi-C2R) framework to continuously update the gallery features extracted by the old model to perform efficient L-ReID in a compatible manner. We verify our proposed Bi-C2R method through theoretical analysis and extensive experiments on multiple benchmarks, which demonstrate that the proposed method can achieve leading performance on both the introduced RFL-ReID task and the traditional L-ReID task.

Related papers

• CFReID: Continual Few-shot Person Re-Identification [127.60234742605832]
  Lifelong ReID has been proposed to learn and accumulate knowledge across multiple domains incrementally.<n>LReID models need to be trained on large-scale labeled data for each unseen domain, which are typically inaccessible due to privacy and cost concerns.<n>We propose Continual Few-shot ReID, which requires models to be incrementally trained using few-shot data and tested on all seen domains.
  arXiv  Detail & Related papers  (2025-03-24T09:17:05Z)
• 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)
• Lifelong Person Re-Identification with Backward-Compatibility [9.94228688034577]
  Lifelong person re-identification (LReID) assumes a practical scenario where the model is sequentially trained on continuously incoming datasets. In this paper, we address the above mentioned problem by incorporating the backward-compatibility to LReID for the first time.
  arXiv  Detail & Related papers  (2024-03-15T05:08:59Z)
• VILLS -- Video-Image Learning to Learn Semantics for Person Re-Identification [51.89551385538251]
  We propose VILLS (Video-Image Learning to Learn Semantics), a self-supervised method that jointly learns spatial and temporal features from images and videos. VILLS first designs a local semantic extraction module that adaptively extracts semantically consistent and robust spatial features. Then, VILLS designs a unified feature learning and adaptation module to represent image and video modalities in a consistent feature space.
  arXiv  Detail & Related papers  (2023-11-27T19:30:30Z)
• Continual Referring Expression Comprehension via Dual Modular Memorization [133.46886428655426]
  Referring Expression (REC) aims to localize an image region of a given object described by a natural-language expression. Existing REC algorithms make a strong assumption that training data feeding into a model are given upfront, which degrades its practicality for real-world scenarios. In this paper, we propose Continual Referring Expression (CREC), a new setting for REC, where a model is learning on a stream of incoming tasks. In order to continuously improve the model on sequential tasks without forgetting prior learned knowledge and without repeatedly re-training from a scratch, we propose an effective baseline method named Dual Modular Memorization
  arXiv  Detail & Related papers  (2023-11-25T02:58:51Z)
• DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior [70.46245698746874]
  We present DiffBIR, a general restoration pipeline that could handle different blind image restoration tasks. DiffBIR decouples blind image restoration problem into two stages: 1) degradation removal: removing image-independent content; 2) information regeneration: generating the lost image content. In the first stage, we use restoration modules to remove degradations and obtain high-fidelity restored results. For the second stage, we propose IRControlNet that leverages the generative ability of latent diffusion models to generate realistic details.
  arXiv  Detail & Related papers  (2023-08-29T07:11:52Z)
• Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation [35.43406281230279]
  Key challenge for Lifelong person re-identification (LReID) is how to incrementally preserve old knowledge and gradually add new capabilities to the system. Inspired by the biological process of human cognition where the somatosensory neocortex and the hippocampus work together in memory consolidation, we formulated a model called Knowledge Refreshing and Consolidation (KRC) KRC achieves both positive forward and backward transfer. More specifically, a knowledge refreshing scheme is incorporated with the knowledge rehearsal mechanism to enable bi-directional knowledge transfer.
  arXiv  Detail & Related papers  (2022-11-29T13:39:45Z)
• 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)
• Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification [10.045028405219641]
  We design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID. We introduce an intra-identity (I$2$-)regularization in the UP-ReID, which is instantiated as two constraints coming from global image aspect and local patch aspect. Our UP-ReID pre-trained model can significantly benefit the downstream ReID fine-tuning and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-12-01T07:16:37Z)
• 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)
• Fine-Grained Re-Identification [1.8275108630751844]
  This paper proposes a computationally efficient fine-grained ReID model, FGReID, which is among the first models to unify image and video ReID. FGReID takes advantage of video-based pre-training and spatial feature attention to improve performance on both video and image ReID tasks.
  arXiv  Detail & Related papers  (2020-11-26T21:04:17Z)

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.