Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification
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 visua
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 57%WildlifeDatasets/wildlife-datasets →
- PossiblePossibly related (embedding) · 47%drivendataorg/zamba →
- PossiblePossibly related (embedding) · 46%Transfer learning with deployment-covariate recalibration for survival prediction under covariate shift →
- LinkedLinked via arxiv author · 85%Anil Osman Tur →
“Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification”
- LinkedLinked via arxiv author · 85%Tonje Knutsen Sordalen →
“Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification”
- LinkedLinked via arxiv author · 85%Kim Tallaksen Halvorsen →
“Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification”
- LinkedLinked via arxiv author · 85%Cigdem Beyan →
“Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification”