SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection
This work addresses modality imbalance and gradient issues in RGB-T salient object detection, offering incremental improvements for computer vision applications.
The paper tackles performance limitations in RGB-T salient object detection by addressing modality imbalance and gradient conflicts, proposing SAMSOD with unimodal supervision and gradient deconfliction, achieving effectiveness across multiple benchmark datasets.
RGB-T salient object detection (SOD) aims to segment attractive objects by combining RGB and thermal infrared images. To enhance performance, the Segment Anything Model has been fine-tuned for this task. However, the imbalance convergence of two modalities and significant gradient difference between high- and low- activations are ignored, thereby leaving room for further performance enhancement. In this paper, we propose a model called \textit{SAMSOD}, which utilizes unimodal supervision to enhance the learning of non-dominant modality and employs gradient deconfliction to reduce the impact of conflicting gradients on model convergence. The method also leverages two decoupled adapters to separately mask high- and low-activation neurons, emphasizing foreground objects by enhancing background learning. Fundamental experiments on RGB-T SOD benchmark datasets and generalizability experiments on scribble supervised RGB-T SOD, fully supervised RGB-D SOD datasets and full-supervised RGB-D rail surface defect detection all demonstrate the effectiveness of our proposed method.