Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification
2026-07-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors developed a method to help computers recognize individual animals over many years despite changes in their looks due to growth or seasons. They improved a popular AI model by adding a way to use continuous numerical information, like time or measurements, during training without needing that information when making predictions. This helps the system adapt smoothly to changes in appearance over time. Their tests on long-term fish and wildlife data showed better results in identifying animals under various conditions.
animal re-identificationCLIPvisual representationmetadata conditioningparameter-efficient adaptationlongitudinal datacross-modal alignmentprompt tuningtemporal distribution shiftsembedding space
Authors
Anil Osman Tur, Tonje Knutsen Sordalen, Kim Tallaksen Halvorsen, Cigdem Beyan
Abstract
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.