DARA：用于抗损坏动物再识别的基于原始到损坏蒸馏的退化感知低秩残差自适应
DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identification
浏览论文内容
中文总结 AI 辅助
研究抗损坏动物再识别，提出DARA方法，冻结微调主干，通过学习低秩残差专家适应退化输入嵌入，结合原始到损坏蒸馏稳定修复，实验证明其在损坏查询检索上表现优异，能推广且计算量小。
中文摘要 AI 辅助
动物再识别依赖细粒度身份线索，易受模糊、噪声、压缩等视觉退化影响。现有基于退化增强训练或像素级恢复的稳健性策略间接提高稳健性，未明确修复身份检索空间中的偏移。本文将抗损坏动物再识别研究为输入条件特征空间修复，并引入DARA，一种用于紧凑再识别模型的轻量级改进方法。DARA冻结微调主干，学习路由低秩残差专家以适应退化输入嵌入，无需损坏类型注释。为稳定此自适应修复，原始到损坏蒸馏使用原始图像教师来保留个体嵌入和检索关系。实验表明DARA在损坏查询检索方面优于标准和基于增强的微调，能推广到未见损坏和跨域评估，在仅增加少量参数和计算量的情况下恢复了大部分损坏查询mAP差距。
英文摘要
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.
发表机构
- The University of Auckland（奥克兰大学）
机构由 AI 辅助整理，请以论文原文为准。
