@inproceedings{wang-etal-2026-benchmarking-fine,
    title = "Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences",
    author = "Wang, Zhen  and
      Zhou, Xi  and
      Yang, Yating  and
      Ma, Bo  and
      Wang, Lei  and
      Dong, Rui  and
      Anwar, Azmat  and
      Miao, Siru",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1525/",
    pages = "30491--30503",
    ISBN = "979-8-89176-395-1",
    abstract = "Existing cross-modal image-text retrieval models often retrieve samples with inconsistent details. To evaluate fine-grained discriminability, we introduce MSCOCO-CCD and Flickr30k-CCD, with three key features: (1) a two-level image content taxonomy for contrastive sample generation and fine-grained evaluation; (2) annotation of numerous contrastive samples, where each sample differs from the anchor by a controlled contrastive difference (CCD), with the specific type of difference labeled; (3) a fine-grained contrastive discrimination metric to assess the ability to distinguish fine-grained nuances. Extensive experiments demonstrate that contrastive samples can significantly degrade retrieval performance. Furthermore, fine-grained evaluation reveals that current models still struggle to effectively produce discriminative representations on certain feature types, such as entity emotion and scene attribute. Our datasets and related codes will be publicly released."
}