DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection
Authors:
Preprint
Abstract
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs). Many state-of-the-art methods impose deep supervision to perform side-output predictions that are linearly aggregated for final saliency prediction. In this paper, we theoretically and experimentally demonstrate that linear aggregation of side-output predictions is suboptimal, and it only makes limited use of the side-output information obtained by deep supervision. To solve this problem, we propose Deeply-supervised Nonlinear Aggregation (DNA) for better leveraging the complementary information of various side-outputs. Compared with existing methods, it i) aggregates side-output features rather than predictions, and ii) adopts nonlinear instead of linear transformations. Experiments demonstrate that DNA can successfully break through the bottleneck of current linear approaches. Specifically, the proposed saliency detector, a modified U-Net architecture with DNA, performs favorably against state-of-the-art methods on various datasets and evaluation metrics without bells and whistles. Code and data will be released upon paper acceptance.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Learning hybrid convolutional features for edge detectionNeurocomputing, 2018
- Contour Knowledge Transfer for Salient Object Detection2018
- Reverse Attention for Salient Object Detection2018
- What is and What is Not a Salient Object? Learning Salient Object Detector by Ensembling Linear Exemplar Regressors2017
- Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach2017
- Saliency Detection with Recurrent Fully Convolutional Networks2016
- Deep Saliency with Encoded Low Level Distance Map and High Level Features2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Deep networks for saliency detection via local estimation and global search2015
- SalientShape: group saliency in image collectionsThe Visual Computer, 2013