papers AI Learner
The Github is limit! Click to go to the new site.

Enhancing Salient Object Segmentation Through Attention

2019-05-27
Anuj Pahuja, Avishek Majumder, Anirban Chakraborty, R. Venkatesh Babu

Abstract

Segmenting salient objects in an image is an important vision task with ubiquitous applications. The problem becomes more challenging in the presence of a cluttered and textured background, low resolution and/or low contrast images. Even though existing algorithms perform well in segmenting most of the object(s) of interest, they often end up segmenting false positives due to resembling salient objects in the background. In this work, we tackle this problem by iteratively attending to image patches in a recurrent fashion and subsequently enhancing the predicted segmentation mask. Saliency features are estimated independently for every image patch, which are further combined using an aggregation strategy based on a Convolutional Gated Recurrent Unit (ConvGRU) network. The proposed approach works in an end-to-end manner, removing background noise and false positives incrementally. Through extensive evaluation on various benchmark datasets, we show superior performance to the existing approaches without any post-processing.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.11522

PDF

https://arxiv.org/pdf/1905.11522


Similar Posts

Comments