The reviewed record of science sign in
Pith

arxiv: 2412.05756 · v1 · pith:2EDYDXOM · submitted 2024-12-07 · cs.CV

Compositional Image Retrieval via Instruction-Aware Contrastive Learning

Reviewed by Pithpith:2EDYDXOMopen to challenge →

classification cs.CV
keywords imagecomposedembeddinginstructionsmodelmultimodaladdresscapability
0
0 comments X
read the original abstract

Composed Image Retrieval (CIR) involves retrieving a target image based on a composed query of an image paired with text that specifies modifications or changes to the visual reference. CIR is inherently an instruction-following task, as the model needs to interpret and apply modifications to the image. In practice, due to the scarcity of annotated data in downstream tasks, Zero-Shot CIR (ZS-CIR) is desirable. While existing ZS-CIR models based on CLIP have shown promising results, their capability in interpreting and following modification instructions remains limited. Some research attempts to address this by incorporating Large Language Models (LLMs). However, these approaches still face challenges in effectively integrating multimodal information and instruction understanding. To tackle above challenges, we propose a novel embedding method utilizing an instruction-tuned Multimodal LLM (MLLM) to generate composed representation, which significantly enhance the instruction following capability for a comprehensive integration between images and instructions. Nevertheless, directly applying MLLMs introduces a new challenge since MLLMs are primarily designed for text generation rather than embedding extraction as required in CIR. To address this, we introduce a two-stage training strategy to efficiently learn a joint multimodal embedding space and further refining the ability to follow modification instructions by tuning the model in a triplet dataset similar to the CIR format. Extensive experiments on four public datasets: FashionIQ, CIRR, GeneCIS, and CIRCO demonstrates the superior performance of our model, outperforming state-of-the-art baselines by a significant margin. Codes are available at the GitHub repository.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering

    cs.CV 2026-04 unverdicted novelty 7.0

    Neighborhood re-ranking via Hungarian matching and query-conditioned local steering improve CLIP retrieval on attribute-binding and compositional tasks by addressing local geometric inconsistencies.

  2. Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent

    cs.CV 2026-06 unverdicted novelty 6.0

    A hybrid LLM agent framework performs universal image clustering by generating guideline-aware embeddings via concept proxies and using MST-based LLM traversal for automatic discovery.