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

arXiv: https://arxiv.org/abs/2607.16644 · HTML: https://mlsanity.com/paper/2607.16644/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 18 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [LoRA+: Efficient Low Rank Adaptation of Large Models](https://mlsanity.com/paper/2402.12354/) (2024)
- [WildlifeDatasets: An open-source toolkit for animal re-identification](https://mlsanity.com/paper/2311.09118/) (2023)
- [UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior](https://mlsanity.com/paper/2501.13134/) (2025)
- [Robust Re-Identification by Multiple Views Knowledge Distillation](https://mlsanity.com/paper/2007.04174/) (2020)
- [Real-world Person Re-Identification via Degradation Invariance Learning](https://mlsanity.com/paper/2004.04933/) (2020)
- [Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification](https://mlsanity.com/paper/2108.00139/) (2021)
- [WildlifeReID-10k: Wildlife re-identification dataset with 10k individual animals](https://mlsanity.com/paper/2406.09211/) (2024)
- [MetaWild: A Multimodal Dataset for Animal Re-Identification with Environmental Metadata](https://mlsanity.com/paper/2501.13368/) (2025)
- [Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment](https://mlsanity.com/paper/2405.13781/) (2024)
- [Auto-selected Knowledge Adapters for Lifelong Person Re-identification](https://mlsanity.com/paper/2405.19005/) (2024)
- [Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification](https://mlsanity.com/paper/2508.06831/) (2025)
- [Dynamic Adapter with Semantics Disentangling for Cross-lingual Cross-modal Retrieval](https://mlsanity.com/paper/2412.13510/) (2024)
- [RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions](https://mlsanity.com/paper/2601.10921/) (2026)
- [Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing](https://mlsanity.com/paper/2602.06862/) (2026)
- [Degradation-based augmented training for robust individual animal re-identification](https://mlsanity.com/paper/2603.04163/) (2026)

## Abstract (arXiv)

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.