From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification

• URL: http://arxiv.org/abs/2604.22190v1
• Date: Fri, 24 Apr 2026 03:37:21 GMT
• Title: From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification
• Abstract summary: We propose SAGA-ReID, which reconstructs identity representations by aligning intermediate patch tokens with anchor vectors parameterized in CLIP's text embedding space.<n> Controlled experiments isolate the aggregation mechanism under two qualitatively distinct conditions.<n> Benchmark evaluations confirm consistent gains over CLIP-ReID across standard and occluded settings.
• Score: 20.74226476678832
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: CLIP-based person re-identification (ReID) methods aggregate spatial features into a single global \texttt{[CLS]} token optimized for image-text alignment rather than spatial selectivity, making representations fragile under occlusion and cross-camera variation. We propose SAGA-ReID, which reconstructs identity representations by aligning intermediate patch tokens with anchor vectors parameterized in CLIP's text embedding space -- emphasizing spatially stable evidence while suppressing corrupted or absent regions, without requiring textual descriptions of individual images. Controlled experiments isolate the aggregation mechanism under two qualitatively distinct conditions -- synthetic masking, where identity signal is absent, and realistic human distractors, where an overlapping person introduces semantically confusing signal -- with SAGA's advantage over global pooling growing substantially as occlusion increases across both conditions. Benchmark evaluations confirm consistent gains over CLIP-ReID across standard and occluded settings, with the largest improvements where global pooling is most unreliable: up to +10.6 Rank-1 on occluded benchmarks. SAGA's aggregation outperforms dedicated sequential patch aggregation on a stronger backbone, confirming that structured reconstruction addresses a bottleneck that backbone quality and architectural complexity alone cannot resolve. Code available at https://github.com/ipl-uw/Structured-Anchor-Guided-Aggregation-for-ReID.

Related papers

• Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery [52.29866804948133]
  We propose CAGI (Cluster-Aware Generative Imputation), a framework that reformulates clustering and imputation as a mutually reinforcing co-optimization process.<n>Experiments on 14 benchmark datasets with 15 representative baselines demonstrate the superiority of CAGI.
  arXiv  Detail & Related papers  (2026-07-08T02:50:02Z)
• Res$^2$CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignment [21.61732087909472]
  Few-shot Generalist Anomaly Detection requires models to generalize to novel categories without retraining.<n>Existing CLIP-based methods face two major challenges: coarse-grained unified text prompts struggle to adapt to fine-grained foreground-background differences.<n>We propose to shift multimodal alignment entirely into a unified residual space, where residual representations naturally eliminate fine-grained normal feature differences.
  arXiv  Detail & Related papers  (2026-05-15T16:49:58Z)
• Zero-Shot Chinese Character Recognition via Global-Local Dual-Branch Alignment and Hierarchical Inference [15.854290215907179]
  Chinese character categories are extremely large, and unseen characters frequently arise in open-world scenarios.<n>Existing IDS-based retrieval methods usually encode a character image and its ideographic description sequence into a single global vector for matching.<n>We propose a Global-Local Hierarchical Perception Network (GL-HPN), which jointly learns global and local representations of character images and IDS sequences.
  arXiv  Detail & Related papers  (2026-05-09T09:05:59Z)
• Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration [41.34371852767098]
  CEA is a token-wise dynamic parameterization framework for all-in-one image restoration.<n>CEA improves average restoration quality over strong prompt-, descriptor-, and expert-based baselines.
  arXiv  Detail & Related papers  (2026-05-07T12:31:24Z)
• Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering [57.38215918201251]
  We propose HERL, a Hyperbolic Enhanced Representation Learning framework for Incomplete Multi-View Clustering.<n> operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning.<n>We show that HERL consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-18T10:50:46Z)
• Entropy-Aware Structural Alignment for Zero-Shot Handwritten Chinese Character Recognition [7.632962062462334]
  Zero-shot Handwritten Chinese Character Recognition aims to recognize unseen characters by leveraging radical-based semantic compositions.<n>We propose an Entropy-Aware Structural Alignment Network that bridges the visual-semantic gap through information-theoretic modeling.<n>Our method establishes new state-of-the-art performance, achieving an accuracy of 55.04% on the ICDAR 2013 dataset.
  arXiv  Detail & Related papers  (2026-02-03T16:08:40Z)
• Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restoration [52.82397287366076]
  All-in-one image restoration aims to handle diverse degradations (e.g., noise, blur, adverse weather) within a unified framework.<n>In this work, we reveal a critical insight: well-crafted feature extraction inherently encodes degradation-carrying information.<n>Our symmetric design preserves intrinsic degradation signals robustly, rendering simple additive fusion in skip connections.
  arXiv  Detail & Related papers  (2025-12-11T12:20:31Z)
• Enhancing CLIP Robustness via Cross-Modality Alignment [54.01929554563447]
  We propose Cross-modality Alignment, an optimal transport-based framework for vision-language models.<n> COLA restores global image-text alignment and local structural consistency in the feature space.<n> COLA is training-free and compatible with existing fine-tuned models.
  arXiv  Detail & Related papers  (2025-10-28T03:47:44Z)
• SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval [4.230223288110963]
  Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image given a reference image and a relative text, without relying on costly triplet annotations.<n>Existing CLIP-based methods face two core challenges: (1) union-based feature fusion indiscriminately aggregates all visual cues, carrying over irrelevant background details that dilute the intended modification, and (2) global cosine similarity from CLIP embeddings lacks the ability to resolve fine-grained semantic relations.
  arXiv  Detail & Related papers  (2025-09-30T09:41:52Z)
• OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction [10.326927761316986]
  Federated clustering aims to discover global cluster structures across decentralized clients without sharing raw data.<n>There are two critical challenges: (1) privacy leakage during collaboration, and (2) robustness degradation due to aggregation of proxy information.<n>We propose Omni Federated Clustering, a unified and model-agnostic framework.
  arXiv  Detail & Related papers  (2025-05-19T13:04:59Z)
• Triplet Contrastive Learning for Unsupervised Vehicle Re-identification [55.445358749042384]
  Part feature learning is a critical technology for fine semantic understanding in vehicle re-identification. We propose a novel Triplet Contrastive Learning framework (TCL) which leverages cluster features to bridge the part features and global features.
  arXiv  Detail & Related papers  (2023-01-23T15:52:12Z)
• Calibrated Feature Decomposition for Generalizable Person Re-Identification [82.64133819313186]
  Calibrated Feature Decomposition (CFD) module focuses on improving the generalization capacity for person re-identification. A calibrated-and-standardized Batch normalization (CSBN) is designed to learn calibrated person representation.
  arXiv  Detail & Related papers  (2021-11-27T17:12:43Z)
• Local-Global Associative Frame Assemble in Video Re-ID [57.7470971197962]
  Noisy and unrepresentative frames in automatically generated object bounding boxes from video sequences cause challenges in learning discriminative representations in video re-identification (Re-ID) Most existing methods tackle this problem by assessing the importance of video frames according to either their local part alignments or global appearance correlations separately. In this work, we explore jointly both local alignments and global correlations with further consideration of their mutual promotion/reinforcement.
  arXiv  Detail & Related papers  (2021-10-22T19:07:39Z)

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.