针对水下图像的复杂退化，提出自适应通道注意力模块提升实例分割精度。
MV-Adapter: Enhancing Underwater Instance Segmentation via Adaptive Channel Attention
- 设计自适应通道注意力机制，动态调整不同通道特征权重。
- 在USIS10K数据集上，mAP、AP50和AP75均有提升。
- 特别适合处理光衰减、色偏和复杂背景的水下场景。
水下实例分割是多种水下视觉任务的基础步骤。然而，复杂水下环境导致的图像质量下降给现有分割模型带来显著挑战。尽管最先进的USIS-SAM模型表现优异，但在应对光衰减、色彩失真和复杂背景时，仍难以有效适应不同通道的特征变化，限制了其在困难水下场景中的分割性能。为此，我们提出海洋视觉适配器（MV-Adapter）。该模块引入自适应通道注意力机制，使模型能根据水下图像特性动态调整各通道的特征权重，从而有效应对光衰减、颜色偏移和复杂背景等问题。实验结果表明，将MV-Adapter模块集成到USIS-SAM网络架构中可进一步提升整体性能，尤其在高精度分割任务中表现突出。在USIS10K数据集上，关键指标如mAP、AP50和AP75均优于对比基线模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。