Bifurcated backbone strategy for RGB-D salient object detection

Abstract

Multi-level feature fusion is a fundamental topic in computer vision. It has been exploited to detect, segment and classify objects at various scales. When multi-level features meet multi-modal cues, the optimal feature aggregation and multi-modal learning strategy become a hot potato. In this paper, we leverage the inherent multi-modal and multi-level nature of RGB-D salient object detection to devise a novel cascaded refinement network. In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS). Second, we introduce a depth-enhanced module (DEM) to excavate informative depth cues from the channel and spatial views. Then, RGB and depth modalities are fused in a complementary way. Our architecture, named Bifurcated Backbone Strategy Network (BBS-Net), is simple, efficient, and backbone-independent. Extensive experiments show that BBS-Net significantly outperforms eighteen SOTA models on eight challenging datasets under five evaluation measures, demonstrating the superiority of our approach ($\sim 4\%$ improvement in S-measure $vs.$ the top-ranked model: DMRA-iccv2019). In addition, we provide a comprehensive analysis on the generalization ability of different RGB-D datasets and provide a powerful training set for future research.

arXiv commentA preliminary version of this work has been accepted in ECCV 2020

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Salient Object Detection: A Benchmark
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
• RGBD Salient Object Detection via Deep Fusion
• RGB-D Salient Object Detection: A Survey
• Bilateral Attention Network for RGB-D Salient Object Detection
• Boundary-guided Feature Aggregation Network for Salient Object Detection

Cited by in corpus (5)

• CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
• Siamese Network for RGB-D Salient Object Detection and Beyond
• Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection
• Densely Deformable Efficient Salient Object Detection Network
• Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration