Assessing Brittleness of Image-Text Retrieval Benchmarks from Vision-Language Models Perspective

We examine the brittleness of the image-text retrieval (ITR) evaluation pipeline with a focus on concept granularity. We start by analyzing two common benchmarks, MS-COCO and Flickr30k, and compare them with augmented, fine-grained versions, MS-COCO-FG and Flickr30k-FG, given a specified set of linguistic features capturing concept granularity. Flickr30k-FG and MS COCO-FG consistently give rise to higher scores across all the selected features. To further our understanding of the impact of granularity we consider a novel taxonomy of query perturbations. We apply these perturbations to the selected datasets. We evaluate four diverse state-of-the-art Vision-Language models on both the standard and fine-grained datasets under zero-shot conditions, with and without the applied perturbations. The results demonstrate that although perturbations generally degrade model performance, the fine-grained datasets exhibit a smaller performance drop than their standard counterparts. The relative performance drop across all setups is consistent across all models and datasets, indicating that the issue lies within the benchmarks themselves. We conclude by providing an agenda for improving ITR evaluation pipelines.