The paper creates FISD, a controlled benchmark for composed image retrieval that removes query ambiguity via generative models, and proposes a multi-round agentic evaluation to assess models in interactive settings.
Im- proving composed image retrieval via contrastive learn- ing with scaling positives and negatives
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
GeCo uses a cGAN-based Complementary Item Generation Model to create target fashion images from seed items and feeds them into a compatibility model for better top-bottom retrieval on three datasets, plus releases a new Fashion Taobao dataset.
Framework uses LLaVA for triplet generation and two-stage fine-tuning to enhance composed fashion image retrieval.
citing papers explorer
-
A Sanity Check on Composed Image Retrieval
The paper creates FISD, a controlled benchmark for composed image retrieval that removes query ambiguity via generative models, and proposes a multi-round agentic evaluation to assess models in interactive settings.
-
Fashion Image-to-Image Translation for Complementary Item Retrieval
GeCo uses a cGAN-based Complementary Item Generation Model to create target fashion images from seed items and feeds them into a compatibility model for better top-bottom retrieval on three datasets, plus releases a new Fashion Taobao dataset.
-
Exploring Multi-Modal Large Language Models and Two-Stage Fine-Tuning for Fashion Image Retrieval
Framework uses LLaVA for triplet generation and two-stage fine-tuning to enhance composed fashion image retrieval.