{"ID":2860510,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.03689","arxiv_id":"2510.03689","title":"SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection","abstract":"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.","short_abstract":"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- acti...","url_abs":"https://arxiv.org/abs/2510.03689","url_pdf":"https://arxiv.org/pdf/2510.03689v1","authors":"[\"Zhengyi Liu\",\"Xinrui Wang\",\"Xianyong Fang\",\"Zhengzheng Tu\",\"Linbo Wang\"]","published":"2025-10-04T06:02:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}