Saliency prediction has achieved significant success in the past decade . However, it still remains challenging to predict saliency maps on images in new domains that lack sufficient data for data-hungry models… To solve this problem, we propose a few-shot transfer learning paradigm for saliency prediction . The proposed framework is gradient-based and model-agnostic . The code is publicly available at \url{https://://://}. The code is public at http://:// framework. We conduct comprehensive experiments and ablation study on various source domain and target domain pairs.

Author(s) :

Links : PDF - Abstract

Code :



Keywords : saliency - prediction - transfer - model - learning -

Leave a Reply

Your email address will not be published. Required fields are marked *