MV-Adapter: Enhancing Underwater Instance Segmentation via Adaptive Channel Attention
This work addresses underwater instance segmentation for marine vision applications, representing an incremental improvement over existing models.
The paper tackles the problem of underwater instance segmentation by proposing MV-Adapter, an adaptive channel attention module that improves the USIS-SAM model's ability to handle underwater image degradation, resulting in enhanced performance metrics like mAP, AP50, and AP75 on the USIS10K dataset.
Underwater instance segmentation is a fundamental and critical step in various underwater vision tasks. However, the decline in image quality caused by complex underwater environments presents significant challenges to existing segmentation models. While the state-of-the-art USIS-SAM model has demonstrated impressive performance, it struggles to effectively adapt to feature variations across different channels in addressing issues such as light attenuation, color distortion, and complex backgrounds. This limitation hampers its segmentation performance in challenging underwater scenarios. To address these issues, we propose the MarineVision Adapter (MV-Adapter). This module introduces an adaptive channel attention mechanism that enables the model to dynamically adjust the feature weights of each channel based on the characteristics of underwater images. By adaptively weighting features, the model can effectively handle challenges such as light attenuation, color shifts, and complex backgrounds. Experimental results show that integrating the MV-Adapter module into the USIS-SAM network architecture further improves the model's overall performance, especially in high-precision segmentation tasks. On the USIS10K dataset, the module achieves improvements in key metrics such as mAP, AP50, and AP75 compared to competitive baseline models.