DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection

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.

arXiv commentarXiv admin note: text overlap with arXiv:1812.10956

References in corpus (8)

• Res2Net: A New Multi-scale Backbone Architecture
• Richer Convolutional Features for Edge Detection
• Deeply supervised salient object detection with short connections
• Video Salient Object Detection via Fully Convolutional Networks
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Review of Visual Saliency Detection with Comprehensive Information
• DISC: Deep Image Saliency Computing via Progressive Representation Learning
• Semantic Edge Detection with Diverse Deep Supervision