Sangwoo Park

Papers from this author

Coarse to Fine: Progressive and Multi-Task Learning for Salient Object Detection

Dong-Goo Kang, Sangwoo Park, Joonki Paik
Track 5: Image and Signal Processing
Wed 13 Jan 2021 at 12:00 in session PS T5.3

Responsive image

Auto-TLDR; Progressive and mutl-task learning scheme for salient object detection

Underline Similar papers

Most deep learning-based salient object detection (SOD) methods tried to manipulate the convolution block to effectively capture the context of object. In this paper, we propose a novel method, called progressive and mutl-task learning scheme, to extract the context of object by only manipulating the learning scheme without changing the network architecture. The progressive learning scheme is a method to grow the decoder progressively in the train phase. In other words, starting from easier low-resolution layers, it gradually adds high-resolution layers. Although the progressive learning successfullyl captures the context of object, its output boundary tends to be rough. To solve this problem, we also propose a multi-task learning (MTL) scheme that processes the object saliency map and contour in a single network jointly. The proposed MTL scheme trains the network in an edge-preserved direction through an auxiliary branch that learns contours. The proposed a learning scheme can be combined with other convolution block manipulation methods. Extensive experiments on five datasets show that the proposed method performs best compared with state-of-the-art methods in most cases.