# Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification

arXiv: https://arxiv.org/abs/2607.09443 · HTML: https://mlsanity.com/paper/2607.09443/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 68 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification](https://mlsanity.com/paper/1903.09776/) (2019)
- [WildlifeDatasets: An open-source toolkit for animal re-identification](https://mlsanity.com/paper/2311.09118/) (2023)
- [A survey of advances in vision-based vehicle re-identification](https://mlsanity.com/paper/1905.13258/) (2019)
- [SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification](https://mlsanity.com/paper/2211.10307/) (2022)
- [SealID: Saimaa ringed seal re-identification dataset](https://mlsanity.com/paper/2206.02260/) (2022)
- [VOC-ReID: Vehicle Re-identification based on Vehicle-Orientation-Camera](https://mlsanity.com/paper/2004.09164/) (2020)
- [Robust Re-identification of Manta Rays from Natural Markings by Learning Pose Invariant Embeddings](https://mlsanity.com/paper/1902.10847/) (2019)
- [Learning landmark guided embeddings for animal re-identification](https://mlsanity.com/paper/2001.02801/) (2020)
- [MetaWild: A Multimodal Dataset for Animal Re-Identification with Environmental Metadata](https://mlsanity.com/paper/2501.13368/) (2025)
- [NORPPA: NOvel Ringed seal re-identification by Pelage Pattern Aggregation](https://mlsanity.com/paper/2206.02498/) (2022)
- [Holstein-Friesian Re-Identification using Multiple Cameras and Self-Supervision on a Working Farm](https://mlsanity.com/paper/2410.12695/) (2024)
- [An Individual Identity-Driven Framework for Animal Re-Identification](https://mlsanity.com/paper/2410.22927/) (2024)
- [A contrastive learning approach for individual re-identification in a wild fish population](https://mlsanity.com/paper/2301.00596/) (2023)

## Built on by (most cited first, 1 of 1)

- [SLAP: Selective Local Vision-Language Alignment for Fish Re-Identification via Partial Optimal Transport](https://mlsanity.com/paper/2608.08840/) (2026)

## Abstract (arXiv)

Long-term animal re-identification (ReID) must remain robust to gradual morphological evolution and seasonal appearance shifts. Although recent vision-language models provide strong pretrained visual representations, adapting them to longitudinal ecological settings remains challenging, particularly under identity and temporal distribution shifts. We present a parameter-efficient CLIP adaptation framework for animal ReID and introduce a continuous metadata-conditioning mechanism that incorporates numerical attributes directly into the prompt representation during training. While low-rank visual adaptation, prompt-based supervision, and cross-modal alignment provide the adaptation framework, the proposed metadata-conditioning strategy constitutes the primary methodological contribution. By preserving the continuous structure of numerical metadata rather than discretizing it into textual categories, the proposed approach enables smooth modulation of the embedding space during training while maintaining a purely visual inference pipeline. Experiments on a seven-year longitudinal fish dataset and multiple wildlife benchmarks demonstrate improved performance under closed-set, open-set, and time-aware evaluation protocols. The results demonstrate that continuous metadata conditioning improves robustness to longitudinal appearance variation and temporal distribution shifts, while parameter-efficient adaptation enables a purely visual inference pipeline without requiring metadata at test time. Code and evaluation splits can be found at: https://github.com/AnilOsmanTur/MetaPrompt-ReID.