Visual Similarity Attention. (arXiv:1911.07381v2 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/1911.07381

While there has been substantial progress in learning suitable distance
metrics, these techniques in general lack transparency and decision reasoning,
i.e., explaining why the input set of images is similar or dissimilar. In this
work, we solve this key problem by proposing the first method to generate
generic visual similarity explanations with gradient-based attention. We
demonstrate that our technique is agnostic to the specific similarity model
type, e.g., we show applicability to Siamese, triplet, and quadruplet models.
Furthermore, we make …

arxiv attention cv