CVMar 4

PinPoint: Evaluation of Composed Image Retrieval with Explicit Negatives, Multi-Image Queries, and Paraphrase Testing

arXiv:2603.04598v1
Originality Incremental advance
AI Analysis

This work provides a more comprehensive benchmark for evaluating Composed Image Retrieval systems, addressing limitations in existing benchmarks for researchers and developers in the field.

This paper introduces PinPoint, a new benchmark for Composed Image Retrieval (CIR) with 7,635 queries and 329K relevance judgments. It reveals that current best methods achieve mAP@10 of 28.5% but retrieve irrelevant results 9% of the time, and show 25.1% performance variation across paraphrases.

Composed Image Retrieval (CIR) has made significant progress, yet current benchmarks are limited to single ground-truth answers and lack the annotations needed to evaluate false positive avoidance, robustness and multi-image reasoning. We present PinPoint, a comprehensive real world benchmark with 7,635 queries and 329K relevance judgments across 23 query categories. PinPoint advances the field by providing: (1) multiple correct answers (averaging 9.1 per query) (2) explicit hard negatives, (3) six instruction paraphrases per query for robustness testing, (4) multi-image composition support (13.4% of queries), and (5) demographic metadata for fairness evaluation. Based on our analysis of 20+ methods across 4 different major paradigms, we uncover three significant drawbacks: The best methods while achieving mAP@10 of 28.5%, still retrieves irrelevant results (hard negatives) 9% of the time. The best models also exhibit 25.1% performance variation across paraphrases, indicating significant potential for enhancing current CIR techniques. Multi-image queries performs 40 to 70% worse across different methods. To overcome these new issues uncovered by our evaluation framework, we propose a training-free reranking method based on an off-the-shelf MLLM that can be applied to any existing system to bridge the gap. We release the complete dataset, including all images, queries, annotations, retrieval index, and benchmarking code.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes