Attribute-Text Guided Forgetting Compensation for Lifelong Person Re-Identification

• URL: http://arxiv.org/abs/2409.19954v1
• Date: Mon, 30 Sep 2024 05:19:09 GMT
• Title: Attribute-Text Guided Forgetting Compensation for Lifelong Person Re-Identification
• Authors: Shiben Liu, Huijie Fan, Qiang Wang, Weihong Ren, Yandong Tang,
• Abstract summary: Lifelong person re-identification (LReID) aims to continuously learn from non-stationary data to match individuals in different environments. Current LReID methods focus on task-specific knowledge and ignore intrinsic task-shared representations within domain gaps. We propose a novel attribute-text guided forgetting compensation model, which explores text-driven global representations and attribute-related local representations.
• Score: 8.841311088024584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Lifelong person re-identification (LReID) aims to continuously learn from non-stationary data to match individuals in different environments. Each task is affected by variations in illumination and person-related information (such as pose and clothing), leading to task-wise domain gaps. Current LReID methods focus on task-specific knowledge and ignore intrinsic task-shared representations within domain gaps, limiting model performance. Bridging task-wise domain gaps is crucial for improving anti-forgetting and generalization capabilities, especially when accessing limited old classes during training. To address these issues, we propose a novel attribute-text guided forgetting compensation (ATFC) model, which explores text-driven global representations of identity-related information and attribute-related local representations of identity-free information for LReID. Due to the lack of paired text-image data, we design an attribute-text generator (ATG) to dynamically generate a text descriptor for each instance. We then introduce a text-guided aggregation network (TGA) to explore robust text-driven global representations for each identity and knowledge transfer. Furthermore, we propose an attribute compensation network (ACN) to investigate attribute-related local representations, which distinguish similar identities and bridge domain gaps. Finally, we develop an attribute anti-forgetting (AF) loss and knowledge transfer (KT) loss to minimize domain gaps and achieve knowledge transfer, improving model performance. Extensive experiments demonstrate that our ATFC method achieves superior performance, outperforming existing LReID methods by over 9.0$\%$/7.4$\%$ in average mAP/R-1 on the seen dataset.

Related papers

• Distribution-aware Knowledge Unification and Association for Non-exemplar Lifelong Person Re-identification [10.062289730759575]
  Lifelong person re-identification (LReID) encounters a key challenge: balancing the preservation of old knowledge with adaptation to new information.<n>We propose a novel distribution-aware knowledge unification and association framework to overcome these limitations.<n> Experimental results show our DKUA outperforms the existing methods by 7.6%/5.3% average mAP/R@1 improvement on anti-forgetting and generalization capacity.
  arXiv  Detail & Related papers  (2025-08-05T14:44:29Z)
• On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation [40.32838937328407]
  A standard adversarial-based framework neglects the discriminability of target-domain features, leading to suboptimal performance.<n>We propose a novel framework that explicitly integrates a domain alignment objective with a discriminability-enhancing constraint.
  arXiv  Detail & Related papers  (2025-05-28T08:24:43Z)
• Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning [13.674493608667627]
  We present a simple approach for cross-domain policy transfer that learns a shared latent representation across domains and a common abstract policy on top of it. Our approach leverages multi-domain behavioral cloning on unaligned trajectories of proxy tasks and employs maximum mean discrepancy (MMD) as a regularization term to encourage cross-domain alignment.
  arXiv  Detail & Related papers  (2024-07-24T00:13:00Z)
• Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement [19.29182848154183]
  Cross-Domain Recommendation (CDR) seeks to enable effective knowledge transfer across domains. While CDR describes user representations as a joint distribution over two domains, these methods fail to account for its joint identifiability. We propose a Hierarchical subspace disentanglement approach to explore the Joint IDentifiability of cross-domain joint distribution.
  arXiv  Detail & Related papers  (2024-04-06T03:11:31Z)
• MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition [9.385527436874096]
  Unsupervised domain adaptation (UDA) aims to improve the performance on the unlabeled target domain. We propose a novel UDA approach for ASR via inter-domain MAtching and intra-domain DIscrimination (MADI) MADI reduces the relative word error rate (WER) on cross-device and cross-environment ASR by 17.7% and 22.8%, respectively.
  arXiv  Detail & Related papers  (2023-02-22T09:11:06Z)
• Adversarial Bi-Regressor Network for Domain Adaptive Regression [52.5168835502987]
  It is essential to learn a cross-domain regressor to mitigate the domain shift. This paper proposes a novel method Adversarial Bi-Regressor Network (ABRNet) to seek more effective cross-domain regression model.
  arXiv  Detail & Related papers  (2022-09-20T18:38:28Z)
• Unsupervised Domain Adaptation via Style-Aware Self-intermediate Domain [52.783709712318405]
  Unsupervised domain adaptation (UDA) has attracted considerable attention, which transfers knowledge from a label-rich source domain to a related but unlabeled target domain. We propose a novel style-aware feature fusion method (SAFF) to bridge the large domain gap and transfer knowledge while alleviating the loss of class-discnative information.
  arXiv  Detail & Related papers  (2022-09-05T10:06:03Z)
• Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement [79.2994130944482]
  We design a Domain Disentanglement Faster-RCNN (DDF) to eliminate the source-specific information in the features for detection task learning. Our DDF method facilitates the feature disentanglement at the global and local stages, with a Global Triplet Disentanglement (GTD) module and an Instance Similarity Disentanglement (ISD) module. By outperforming state-of-the-art methods on four benchmark UDA object detection tasks, our DDF method is demonstrated to be effective with wide applicability.
  arXiv  Detail & Related papers  (2022-01-06T05:43:01Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)
• Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification [87.72851934197936]
  Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching. One challenge is how to generate target domain samples with reliable labels for training. We propose a Disentanglement-based Cross-Domain Feature Augmentation strategy.
  arXiv  Detail & Related papers  (2021-03-25T15:28:41Z)
• Interventional Domain Adaptation [81.0692660794765]
  Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Standard domain-invariance learning suffers from spurious correlations and incorrectly transfers the source-specifics. We create counterfactual features that distinguish the domain-specifics from domain-sharable part.
  arXiv  Detail & Related papers  (2020-11-07T09:53:13Z)
• Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation [70.45936509510528]
  Partial domain adaptation aims to adapt knowledge from a larger and more diverse source domain to a smaller target domain with less number of classes. Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain. It is essential to align target data with only a small set of source data.
  arXiv  Detail & Related papers  (2020-08-26T03:18:53Z)

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.