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 popular 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 26 references indexed in Scilit:
- Learning hybrid convolutional features for edge detectionNeurocomputing, 2018
- Review of Visual Saliency Detection With Comprehensive InformationIEEE Transactions on Circuits and Systems for Video Technology, 2018
- Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A SurveyIEEE Signal Processing Magazine, 2018
- Video Saliency Detection Using Object ProposalsIEEE Transactions on Cybernetics, 2017
- Higher Order Energies for Image SegmentationIEEE Transactions on Image Processing, 2017
- DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object DetectionIEEE Transactions on Image Processing, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- SalientShape: group saliency in image collectionsThe Visual Computer, 2013
- Region-Based Saliency Detection and Its Application in Object RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2013
- Visual-Textual Joint Relevance Learning for Tag-Based Social Image SearchIEEE Transactions on Image Processing, 2012