Pith. sign in

REVIEW 2 cited by

Compositional Image Retrieval via Instruction-Aware Contrastive Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

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

classification cs.CV
keywords imagecomposedembeddinginstructionsmodelmultimodaladdresscapability
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A zero-shot composed image retrieval model trained on synthetic triplets, generated by an MLLM from moderately similar unlabeled image pairs, beats prior methods on three benchmarks.

  2. MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval

    cs.CV 2025-05 conditional novelty 6.0 of 10

    MVFT-JI trains a Q-Former VLM with two MLLM-generated retrieval tasks and fuses VLM and MLLM similarities at inference, achieving state-of-the-art zero-shot composed image retrieval on three benchmarks.

Pith tools