Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets

• URL: http://arxiv.org/abs/2606.07032v1
• Date: Fri, 05 Jun 2026 08:23:25 GMT
• Title: Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets
• Abstract summary: Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption without training samples.<n>Existing ZS-CIR datasets often suffer from complete irrelevance between reference and target images due to noisy image sources.<n>We introduce ZeroSight, a novel benchmark for ZS-CIR.
• Score: 61.420656457977195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption without training samples. Existing ZS-CIR datasets often suffer from complete irrelevance between reference and target images due to noisy image sources, and do not achieve a true zero-shot scenario as they use public image datasets that models like CLIP have been trained on. To tackle these challenges, we introduce ZeroSight, a novel benchmark for ZS-CIR. It includes a dataset with consistent reference-target pairs sourced from videos, a data construction pipeline, and evaluation methods that consider the ranking of multiple positive and negative target images. We ensure visually and semantically consistent reference-target pairs by extracting frames from a single video and generating relative captions using LLM-assisted methods. To ensure a true zero-shot scenario, we use video data published after March 31, 2022, ensuring it was not included in CLIP's pre-training data. Additionally, we propose a training-free MLLM-driven method, SC4CIR (Symmetric Consistency for CIR), which can effectively identify hard negative targets through 3 symmetric consistency checks. This method is plug-and-play, seamlessly integrating with various CIR methods and significantly improving performance. Our experimental results from 27 methods reveal that current ZS-CIR datasets and evaluation metrics result in inflated retrieval performance, exaggerating the capabilities of CIR methods. Our benchmark and models can be accessed at https://github.com/sotayang/ZeroSight.

Related papers

• DiCE-CIR: Direct Composition Learning for Efficient Zero-Shot Composed Image Retrieval [52.15696141238419]
  Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image from a multimodal query consisting of a reference image and an edit text.<n>We propose DiCE-CIR, a direct composition learning method that predicts composed query representations by directly composing a reference image and an edit text.
  arXiv  Detail & Related papers  (2026-07-06T04:37:30Z)
• SDR-CIR: Semantic Debias Retrieval Framework for Training-Free Zero-Shot Composed Image Retrieval [10.874487857707038]
  Composed Image Retrieval (CIR) aims to retrieve a target image from a query composed of a reference image and modification text.<n>We propose SDR-CIR, a training-free Semantic Debias Ranking method based on Chain-of-Thought reasoning.
  arXiv  Detail & Related papers  (2026-02-04T11:24:35Z)
• Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval [52.709090256954276]
  Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images given a compositional query.<n>We propose a novel framework by employing a Multimodal Reasoning Agent (MRA) for ZS-CIR.
  arXiv  Detail & Related papers  (2025-05-26T13:17:50Z)
• SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [74.40683913645731]
  Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications.<n>Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth.<n>Analysis of these prompt scores reveals VLM biases and AND''/OR' signal ambiguities, notably that maximum scores are surprisingly suboptimal compared to second-highest scores.
  arXiv  Detail & Related papers  (2025-02-24T07:15:05Z)
• HyCIR: Boosting Zero-Shot Composed Image Retrieval with Synthetic Labels [5.34016463729574]
  Composed Image Retrieval (CIR) aims to retrieve images based on a query image with text. Current Zero-Shot CIR (ZS-CIR) methods try to solve CIR tasks without using expensive triplet-labeled training datasets. We propose Hybrid CIR (HyCIR), which uses synthetic labels to boost the performance of ZS-CIR.
  arXiv  Detail & Related papers  (2024-07-08T09:55:36Z)
• iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval [26.101116761577796]
  Composed Image Retrieval (CIR) aims to retrieve target images visually similar to the reference one while incorporating the changes specified in the relative caption.<n>We introduce a new task, Zero-Shot CIR (ZS-CIR), that addresses CIR without the need for a labeled training dataset.<n>We present an open-domain benchmarking dataset named CIRCO, where each query is labeled with multiple ground truths and a semantic categorization.
  arXiv  Detail & Related papers  (2024-05-05T14:39:06Z)
• Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval [50.72924579220149]
  Composed Image Retrieval (CIR) is a task that retrieves images similar to a query, based on a provided textual modification. Current techniques rely on supervised learning for CIR models using labeled triplets of the reference image, text, target image. We propose a new semi-supervised CIR approach where we search for a reference and its related target images in auxiliary data.
  arXiv  Detail & Related papers  (2024-04-23T21:00:22Z)
• Zero-Shot Composed Image Retrieval with Textual Inversion [28.513594970580396]
  Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption. We propose a new task, Zero-Shot CIR (ZS-CIR), that aims to address CIR without requiring a labeled training dataset.
  arXiv  Detail & Related papers  (2023-03-27T14:31:25Z)
• Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval [84.11127588805138]
  Composed Image Retrieval (CIR) combines a query image with text to describe their intended target. Existing methods rely on supervised learning of CIR models using labeled triplets consisting of the query image, text specification, and the target image. We propose Zero-Shot Composed Image Retrieval (ZS-CIR), whose goal is to build a CIR model without requiring labeled triplets for training.
  arXiv  Detail & Related papers  (2023-02-06T19:40:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.