Disentangled High Quality Salient Object Detection
Preprint
Abstract
Aiming at discovering and locating most distinctive objects from visual scenes, salient object detection (SOD) plays an essential role in various computer vision systems. Coming to the era of high resolution, SOD methods are facing new challenges. The major limitation of previous methods is that they try to identify the salient regions and estimate the accurate objects boundaries simultaneously with a single regression task at low-resolution. This practice ignores the inherent difference between the two difficult problems, resulting in poor detection quality. In this paper, we propose a novel deep learning framework for high-resolution SOD task, which disentangles the task into a low-resolution saliency classification network (LRSCN) and a high-resolution refinement network (HRRN). As a pixel-wise classification task, LRSCN is designed to capture sufficient semantics at low-resolution to identify the definite salient, background and uncertain image regions. HRRN is a regression task, which aims at accurately refining the saliency value of pixels in the uncertain region to preserve a clear object boundary at high-resolution with limited GPU memory. It is worth noting that by introducing uncertainty into the training process, our HRRN can well address the high-resolution refinement task without using any high-resolution training data. Extensive experiments on high-resolution saliency datasets as well as some widely used saliency benchmarks show that the proposed method achieves superior performance compared to the state-of-the-art methods.Keywords
All Related Versions
This publication has 52 references indexed in Scilit:
- Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection2020
- Highly Efficient Salient Object Detection with 100K Parameters2020
- Suppress and Balance: A Simple Gated Network for Salient Object Detection2020
- Salient Object Detection: A Discriminative Regional Feature Integration ApproachInternational Journal of Computer Vision, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Visual saliency based on multiscale deep features2015
- The Secrets of Salient Object Segmentation2014
- Saliency Detection via Graph-Based Manifold Ranking2013
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998