TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network

Abstract

Salient object detection is the pixel-level dense prediction task which can highlight the prominent object in the scene. Recently U-Net framework is widely used, and continuous convolution and pooling operations generate multi-level features which are complementary with each other. In view of the more contribution of high-level features for the performance, we propose a triplet transformer embedding module to enhance them by learning long-range dependencies across layers. It is the first to use three transformer encoders with shared weights to enhance multi-level features. By further designing scale adjustment module to process the input, devising three-stream decoder to process the output and attaching depth features to color features for the multi-modal fusion, the proposed triplet transformer embedding network (TriTransNet) achieves the state-of-the-art performance in RGB-D salient object detection, and pushes the performance to a new level. Experimental results demonstrate the effectiveness of the proposed modules and the competition of TriTransNet.

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• Transformer in Transformer
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
• Visual Transformers: Token-based Image Representation and Processing for Computer Vision
• Escaping the Big Data Paradigm with Compact Transformers
• LocalViT: Analyzing Locality in Vision Transformers
• Bilateral Attention Network for RGB-D Salient Object Detection
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Depth Quality Aware Salient Object Detection
• Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection
• Point Transformer
• Global-Local Propagation Network for RGB-D Semantic Segmentation

Cited by in corpus (10)

• CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
• ${\mathbf{C}}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection
• HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness
• HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection
• Salient Object Detection in Optical Remote Sensing Images Driven by Transformer
• Middle-level Fusion for Lightweight RGB-D Salient Object Detection
• Quality-aware Selective Fusion Network for V-D-T Salient Object Detection
• Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection
• ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection
• Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion