DART$^3$: Leveraging Distance for Test Time Adaptation in Person Re-Identification

• URL: http://arxiv.org/abs/2505.18337v1
• Date: Fri, 23 May 2025 19:46:20 GMT
• Title: DART$^3$: Leveraging Distance for Test Time Adaptation in Person Re-Identification
• Authors: Rajarshi Bhattacharya, Shakeeb Murtaza, Christian Desrosiers, Jose Dolz, Maguelonne Heritier, Eric Granger,
• Abstract summary: Person re-identification (ReID) models suffer from camera bias, where learned representations cluster according to camera viewpoints rather than identity.<n>We introduce DART$3$, a TTA framework specifically designed to mitigate camera-induced domain shifts in person ReID.
• Score: 20.378299237413177
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Person re-identification (ReID) models are known to suffer from camera bias, where learned representations cluster according to camera viewpoints rather than identity, leading to significant performance degradation under (inter-camera) domain shifts in real-world surveillance systems when new cameras are added to camera networks. State-of-the-art test-time adaptation (TTA) methods, largely designed for classification tasks, rely on classification entropy-based objectives that fail to generalize well to ReID, thus making them unsuitable for tackling camera bias. In this paper, we introduce DART$^3$, a TTA framework specifically designed to mitigate camera-induced domain shifts in person ReID. DART$^3$ (Distance-Aware Retrieval Tuning at Test Time) leverages a distance-based objective that aligns better with image retrieval tasks like ReID by exploiting the correlation between nearest-neighbor distance and prediction error. Unlike prior ReID-specific domain adaptation methods, DART$^3$ requires no source data, architectural modifications, or retraining, and can be deployed in both fully black-box and hybrid settings. Empirical evaluations on multiple ReID benchmarks indicate that DART$^3$ and DART$^3$ LITE, a lightweight alternative to the approach, consistently outperforms state-of-the-art TTA baselines, making for a viable option to online learning to mitigate the adverse effects of camera bias.

Related papers

• Exploring the Camera Bias of Person Re-identification [18.605398174512295]
  We measure the camera bias of ReID models on unseen domains and reveal that camera bias becomes more pronounced under data distribution shifts.<n>As a debiasing method for unseen domain data, we revisit feature normalization on embedding vectors.<n>We show that this simple method is effective at reducing bias and show that it can be applied to detailed bias factors such as low-level image properties and body angle.
  arXiv  Detail & Related papers  (2025-02-14T14:39:24Z)
• Low Saturation Confidence Distribution-based Test-Time Adaptation for Cross-Domain Remote Sensing Image Classification [4.7514513970228425]
  Unsupervised Domain Adaptation (UDA) has emerged as a powerful technique for addressing the distribution shift across various Remote Sensing (RS) applications.<n>Most UDA approaches require access to source data, which may be infeasible due to data privacy or transmission constraints.<n>Low Saturation Confidence Distribution Test-Time Adaptation (D-TTA) marketing the first attempt to explore Test-Time Adaptation for cross-domain RS image classification.
  arXiv  Detail & Related papers  (2024-08-29T05:04:25Z)
• Towards Generalizable Multi-Camera 3D Object Detection via Perspective Debiasing [28.874014617259935]
  Multi-Camera 3D Object Detection (MC3D-Det) has gained prominence with the advent of bird's-eye view (BEV) approaches. We propose a novel method that aligns 3D detection with 2D camera plane results, ensuring consistent and accurate detections.
  arXiv  Detail & Related papers  (2023-10-17T15:31:28Z)
• Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling [38.07637524378327]
  Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. Existing DA methods suffer from a substantial drop in performance when applied to a multi-class training setting. We propose a novel ReDB framework tailored for learning to detect all classes at once.
  arXiv  Detail & Related papers  (2023-07-16T04:34:11Z)
• 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)
• Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution [114.26933742226115]
  Super-resolution (SR) models trained on images from different devices could exhibit distinct imaging patterns. We propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA) We empirically conduct experiments under six Real to Real adaptation settings among three different cameras, and achieve superior performance compared with existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-05-07T02:55:39Z)
• Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-Identification [4.5471611558189124]
  We propose camera-tracklet-aware contrastive learning (CTACL) using the multi-camera tracklet information without vehicle identity labels. The proposed CTACL divides an unlabelled domain, i.e., entire vehicle images, into multiple camera-level images and conducts contrastive learning. We demonstrate the effectiveness of our approach on video-based and image-based vehicle Re-ID datasets.
  arXiv  Detail & Related papers  (2021-09-14T02:12:54Z)
• 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)
• Unsupervised and self-adaptative techniques for cross-domain person re-identification [82.54691433502335]
  Person Re-Identification (ReID) across non-overlapping cameras is a challenging task. Unsupervised Domain Adaptation (UDA) is a promising alternative, as it performs feature-learning adaptation from a model trained on a source to a target domain without identity-label annotation. In this paper, we propose a novel UDA-based ReID method that takes advantage of triplets of samples created by a new offline strategy.
  arXiv  Detail & Related papers  (2021-03-21T23:58:39Z)
• 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)
• Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation [51.17232267143098]
  We propose a novel system named Disp R-CNN for 3D object detection from stereo images. We use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds. Experiments on the KITTI dataset show that, even when LiDAR ground-truth is not available at training time, Disp R-CNN achieves competitive performance and outperforms previous state-of-the-art methods by 20% in terms of average precision.
  arXiv  Detail & Related papers  (2020-04-07T17:48:45Z)
• 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.