Most existing RGB-D SOD models have no cross-modal interactions or have unidirectional interactions from depth to RGB in their encoder stages . We propose to conduct progressivebi-directional interactions as early in the encoder stage . We also design an effective light-weight group decoder to achieve accurate final saliencyprediction . Comprehensive experiments on six widely used datasets demonstratethat BTS-Net surpasses 16 latest state-of-the-art approaches in terms of four key metrics . The resulting results are based on the resulting robust encoder features, we also designan effective .

Author(s) : Wenbo Zhang, Yao Jiang, Keren Fu, Qijun Zhao

Links : PDF - Abstract

Code :

https://github.com/alsoj/Recommenders-movielens


Coursera

Keywords : rgb - interactions - encoder - resulting - bts -

Leave a Reply

Your email address will not be published.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