@inproceedings{donmez-etal-2023-hnc,
    title = "{HNC}: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities",
    author = {D{\"o}nmez, Esra  and
      Tilli, Pascal  and
      Yang, Hsiu-Yu  and
      Vu, Ngoc Thang  and
      Silberer, Carina},
    editor = "Jiang, Jing  and
      Reitter, David  and
      Deng, Shumin",
    booktitle = "Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.conll-1.24/",
    doi = "10.18653/v1/2023.conll-1.24",
    pages = "364--388",
    abstract = "Image-Text-Matching (ITM) is one of the defacto methods of learning generalized representations from a large corpus in Vision and Language (VL). However, due to the weak association between the web-collected image{--}text pairs, models fail to show fine-grained understanding of the combined semantics of these modalities. To this end, we propose Hard Negative Captions (HNC): an automatically created dataset containing foiled hard negative captions for ITM training towards achieving fine-grained cross-modal comprehension in VL. Additionally, we provide a challenging manually-created test set for benchmarking models on a fine-grained cross-modal mismatch with varying levels of compositional complexity. Our results show the effectiveness of training on HNC by improving the models' zero-shot capabilities in detecting mismatches on diagnostic tasks and performing robustly under noisy visual input scenarios. Also, we demonstrate that HNC models yield a comparable or better initialization for fine-tuning. Our code and data are publicly available."
}