A Baseline for Detecting Out-of-Distribution Examples in Image Captioning
Gal Shalev, Gabi Shalev, Joseph Keshet · Proceedings of the 30th ACM International Conference on Multimedia · 2022
Image captioning research achieved breakthroughs in recent years by developing neural models that can generate diverse and high-quality descriptions for images drawn from the same distribution as training images. However, when facing out-of-distribution (OOD) images, such as corrupted images, or images containing unknown objects, the models fail in generating relevant captions.