SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection

TL;DR

SwinNet leverages Swin Transformer and edge-guided fusion to enhance salient object detection in RGB-D and RGB-T images, outperforming existing models by effectively capturing hierarchical features and boundary details.

Contribution

The paper introduces a novel cross-modality fusion model using Swin Transformer and edge guidance for improved RGB-D and RGB-T salient object detection.

Findings

Outperforms state-of-the-art models on multiple datasets.

Effectively captures hierarchical and boundary features.

Enhances cross-modality feature fusion.

Abstract

Convolutional neural networks (CNNs) are good at extracting contexture features within certain receptive fields, while transformers can model the global long-range dependency features. By absorbing the advantage of transformer and the merit of CNN, Swin Transformer shows strong feature representation ability. Based on it, we propose a cross-modality fusion model SwinNet for RGB-D and RGB-T salient object detection. It is driven by Swin Transformer to extract the hierarchical features, boosted by attention mechanism to bridge the gap between two modalities, and guided by edge information to sharp the contour of salient object. To be specific, two-stream Swin Transformer encoder first extracts multi-modality features, and then spatial alignment and channel re-calibration module is presented to optimize intra-level cross-modality features. To clarify the fuzzy boundary, edge-guided decoder achieves inter-level cross-modality fusion under the guidance of edge features. The proposed model outperforms the state-of-the-art models on RGB-D and RGB-T datasets, showing that it provides more insight into the cross-modality complementarity task.