Bilateral Attention Network for RGB-D Salient Object Detection

Abstract

Most existing RGB-D salient object detection (SOD) methods focus on the foreground region when utilizing the depth images. However, the background also provides important information in traditional SOD methods for promising performance. To better explore salient information in both foreground and background regions, this paper proposes a Bilateral Attention Network (BiANet) for the RGB-D SOD task. Specifically, we introduce a Bilateral Attention Module (BAM) with a complementary attention mechanism: foreground-first (FF) attention and background-first (BF) attention. The FF attention focuses on the foreground region with a gradual refinement style, while the BF one recovers potentially useful salient information in the background region. Benefitted from the proposed BAM module, our BiANet can capture more meaningful foreground and background cues, and shift more attention to refining the uncertain details between foreground and background regions. Additionally, we extend our BAM by leveraging the multi-scale techniques for better SOD performance. Extensive experiments on six benchmark datasets demonstrate that our BiANet outperforms other state-of-the-art RGB-D SOD methods in terms of objective metrics and subjective visual comparison. Our BiANet can run up to 80fps on $224\times 224$ RGB-D images, with an NVIDIA GeForce RTX 2080Ti GPU. Comprehensive ablation studies also validate our contributions.

References in corpus (10)

• Res2Net: A New Multi-scale Backbone Architecture
• Salient Object Detection: A Benchmark
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• Deeply supervised salient object detection with short connections
• Review of Visual Saliency Detection with Comprehensive Information
• RGBD Salient Object Detection via Deep Fusion
• RANet: Ranking Attention Network for Fast Video Object Segmentation
• Cross-Modal Attentional Context Learning for RGB-D Object Detection
• Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss
• Super Diffusion for Salient Object Detection

Cited by in corpus (11)

• RGB-D Salient Object Detection: A Survey
• Multi-interactive Dual-decoder for RGB-thermal Salient Object Detection
• CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
• CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Bifurcated backbone strategy for RGB-D salient object detection
• TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network
• HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness
• Middle-level Fusion for Lightweight RGB-D Salient Object Detection
• Implicit Ray-Transformers for Multi-view Remote Sensing Image Segmentation
• Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidance