ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval
A fashion-specialized vision-language model achieves superior retrieval performance through full fine-tuning with knowledge distillation and weight interpolation, outperforming exi…
Hugging Face · Daily Papers
·Siqiao Xue, Chunxue Xu
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Siqiao Xue, Chunxue Xu
- 3 upvotes da comunidade
- Temas: vision-language encoder, fashion retrieval, full fine-tuning, knowledge distillation, weight interpolation, SigLIP2-base
Resumo
Resumo original (em inglês), extraído do paper:
A fashion-specialized vision-language model achieves superior retrieval performance through full fine-tuning with knowledge distillation and weight interpolation, outperforming existing methods on a new benchmark while addressing structural biases in existing datasets.Onde ler
// relacionados
Leia também
Blog
Linq’s iMessage Apps Bring Payments, Tickets, Flights, and Games Into the iMessage Bubble Through the imessage_app Part
Blog
The DeepMind trio who built a poker AI are now making money for quant hedge funds
Dataset
hotdogs/uka-fable-reasoning
Blog