ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval

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

compartilhar: