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.
Compodiff: Versatile composed image retrieval with latent diffusion
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5representative citing papers
STiTch refines LLM captions via embedding transition and uses set-to-set bidirectional transportation alignment to improve training-free zero-shot composed image retrieval.
Presents ChatSearch dataset and ChatSearcher generative model for conversational image retrieval on open-domain images, claiming superior performance on the new dataset and competitive results elsewhere.
A hierarchical multi-agent framework that fuses three CLIP-based retrieval views and then applies tournament-style test-time reasoning reports the best published scores on CIRR, CIRCO, and FashionIQ.
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.
-
STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval
STiTch refines LLM captions via embedding transition and uses set-to-set bidirectional transportation alignment to improve training-free zero-shot composed image retrieval.
-
ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval
Presents ChatSearch dataset and ChatSearcher generative model for conversational image retrieval on open-domain images, claiming superior performance on the new dataset and competitive results elsewhere.
-
DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval
A hierarchical multi-agent framework that fuses three CLIP-based retrieval views and then applies tournament-style test-time reasoning reports the best published scores on CIRR, CIRCO, and FashionIQ.
-
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.