Let there be a clock on the beach

Ali Furkan Biten, Lluis Gomez, Dimosthenis KaratzasWACV 2022 · OpenReview

Abstract

Explaining an image with missing or non-existent objects is known as object bias (hallucination) in image captioning. This behaviour is quite common in the state-of-the-art captioning models which is not desirable by humans. To decrease the object hallucination in captioning, we propose three simple yet efficient training augmentation method for sentences which requires no new training data or increase in the model size. By extensive analysis, we show that the proposed methods can significantly diminish our models' object bias on hallucination metrics. Moreover, we experimentally demonstrate that our methods decrease the dependency on the visual features. All of our code, configuration files and model weights are available online1.
BibTeX
@inproceedings{biten2022let,
  author = {Ali Furkan Biten and Lluis Gomez and Dimosthenis Karatzas},
  title = {{Let there be a clock on the beach}},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year = {2022},
  url = {https://openreview.net/forum?id=nrueb00sCS},
}

Loading related content...

Figure