Siamese Network for RGB-D Salient Object Detection and Beyond

Abstract

Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately designed training process. Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture. In this paper, we propose two effective components: joint learning (JL), and densely cooperative fusion (DCF). The JL module provides robust saliency feature learning by exploiting cross-modal commonality via a Siamese network, while the DCF module is introduced for complementary feature discovery. Comprehensive experiments using five popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the state-of-the-art models by an average of ~2.0% (max F-measure) across seven challenging datasets. In addition, we show that JL-DCF is readily applicable to other related multi-modal detection tasks, including RGB-T (thermal infrared) SOD and video SOD, achieving comparable or even better performance against state-of-the-art methods. We also link JL-DCF to the RGB-D semantic segmentation field, showing its capability of outperforming several semantic segmentation models on the task of RGB-D SOD. These facts further confirm that the proposed framework could offer a potential solution for various applications and provide more insight into the cross-modal complementarity task.

arXiv commentarXiv admin note: substantial text overlap with arXiv:2004.08515

References in corpus (11)

• Res2Net: A New Multi-scale Backbone Architecture
• Computing the Stereo Matching Cost with a Convolutional Neural Network
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• 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
• Deep Learning for Visual Tracking: A Comprehensive Survey
• Indoor Semantic Segmentation using depth information
• Bifurcated backbone strategy for RGB-D salient object detection
• RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation
• UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders

Cited by in corpus (6)

• Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models
• Effectiveness Assessment of Recent Large Vision-Language Models
• Uncertainty Inspired RGB-D Saliency Detection
• RGB-D Tracking via Hierarchical Modality Aggregation and Distribution Network
• Densely Deformable Efficient Salient Object Detection Network
• Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration