CORTEXA
← Browse
arxivcs.CV2026-07-18

DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identification

Cynthia Xie, Talia Xu

Animal re-identification (Re-ID) relies on fine-grained identity cues that can be disrupted by blur, noise, compression, and other visual degradations. Existing robustness strategies based on degradation-augmented training or pixel-level restoration improve robustness indirectly, but do not explicitly repair shifts in the identity retrieval space. We study corruption-robust animal Re-ID as input-conditioned feature-space repair and introduce DARA, a lightweight retrofit for compact Re-ID models. DARA freezes the fine-tuned backbone and learns routed low-rank residual experts to adapt degraded-input embeddings without corruption-type annotations. To stabilize this adaptive repair, original-to-corrupted distillation uses an original-image teacher to preserve individual embeddings and retrieval relations. Experiments on ATRW, FriesianCattle2017, MPDD, and SeaStarReID2023 show that DARA improves corrupted-query retrieval over standard and augmentation-based fine-tuning, generalizes to unseen corruptions and cross-domain evaluation, and recovers 77.0% of the corrupted-query mAP gap to full corrupted fine-tuning while adding only 0.49% parameters and 0.05% FLOPs.

View free PDFSource page

Related papers

arxivcs.CV2026-07-21

Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching

Xin Xu, Shuhao Zhan, Wei Liu, Zheng Wang, Kui Jiang, Chia-Wen Lin

Visible-Infrared Person Re-Identification (VI-ReID) operates under a closed-world assumption, where queries and galleries are from heterogeneous modalities. However, in open-world scenarios, both sets are likely to contain homogeneous and heterogeneous modality images. A query ma…

View free PDFSource page
arxivcs.CVcs.LG2026-07-24

Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification in the Foundation-Model Era

Yu Wang, Hongyu Yang

Multi-branch architectures and CNN-Transformer fusion have long been regarded as effective ways to improve vehicle re-identification (Re-ID) by combining complementary representations. In this work, we revisit this assumption in the foundation-model era through a comprehensive em…

View free PDFSource page
arxivcs.CV2026-07-31

Multi-Modal Object Re-Identification with Dual Semantic Guidance and Global-Local Mutual Modulation

Weixiang Zhou, Xingguo Xu, Yuhao Wang, Cong Wang, Yang Yang, Zhixun Su, et al.

Multi-modal object Re-Identification (ReID) aims to retrieve target instances by leveraging complementary information across modalities. However, existing methods suffer from two challenges. First, they often fail to exploit well-aligned and reliable semantic priors, making them…

View free PDFSource page
arxivcs.CVcs.LG2026-07-23

DART: A Degradation-Aware Recurrent Transformer for Archival Film Restoration

Mikołaj Jastrzębski, Wojciech Kozłowski, Kamil Adamczewski

Archival film restoration is a challenging problem because historical footage contains compound degradations such as scratches, dust, blur, noise, flicker, and photometric aging, while clean reference videos are unavailable. Existing video restoration methods largely treat these…

View free PDFSource page
arxivcs.CVq-bio.NC2026-07-31

Multi-Source Multi-View Graph Domain Adaptation with Hyperbolic Residual Encoding for Cross-Site MDD Identification from rs-fMRI

Zhanpeng Zheng, Xiran Chen, Haiteng Jiang, Renjie Tian, Qinyu Cai, Jiexi Liu, et al.

Cross-site identification of major depressive disorder (MDD) from resting-state functional magnetic resonance imaging (rs-fMRI) is hindered by inter-site distribution shifts and heterogeneous functional connectivity (FC) views. These views capture complementary neural relationshi…

View free PDFSource page
arxivcs.CV2026-07-31

Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark

Muyao Niu, Mingze Ma, Yifan Zhan, Qingtian Zhu, Zhihang Zhong, Wei Guo, et al.

Robust low-light imaging remains challenging for the community. Recent studies have explored fusing Near-Infrared (NIR) with noisy RGB to achieve improved enhancement, yet most methods depend on carefully curated training data pairs, with limited robustness under different scenar…

View free PDFSource page