# MV-Adapter: Enhancing Underwater Instance Segmentation via Adaptive Channel Attention

arXiv: https://arxiv.org/abs/2411.00472 · HTML: https://mlsanity.com/paper/2411.00472/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 1 Nov 2024.

## Builds on (most cited first, 19 of 19)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems](https://mlsanity.com/paper/1901.06455/) (2019)
- [Underwater Ranker: Learn Which Is Better and How to Be Better](https://mlsanity.com/paper/2208.06857/) (2022)
- [Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset](https://mlsanity.com/paper/2406.06039/) (2024)
- [Experiments of Federated Learning for COVID-19 Chest X-ray Images](https://mlsanity.com/paper/2007.05592/) (2020)
- [Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Data](https://mlsanity.com/paper/1912.12204/) (2019)
- [Computer Vision and Deep Learning for Fish Classification in Underwater Habitats: A Survey](https://mlsanity.com/paper/2203.06951/) (2022)
- [Peer-Assisted Robotic Learning: A Data-Driven Collaborative Learning Approach for Cloud Robotic Systems](https://mlsanity.com/paper/2010.08303/) (2020)
- [AuthROS: Secure Data Sharing Among Robot Operating Systems Based on Ethereum](https://mlsanity.com/paper/2208.14269/) (2022)
- [ElasticROS: An Elastically Collaborative Robot Operation System for Fog and Cloud Robotics](https://mlsanity.com/paper/2209.01774/) (2022)
- [EdgeLoc: A Communication-Adaptive Parallel System for Real-Time Localization in Infrastructure-Assisted Autonomous Driving](https://mlsanity.com/paper/2405.12120/) (2024)
- [LLM-Slice: Dedicated Wireless Network Slicing for Large Language Models](https://mlsanity.com/paper/2410.18499/) (2024)
- [On the limits of perceptual quality measures for enhanced underwater images](https://mlsanity.com/paper/2207.05470/) (2022)

## Abstract (arXiv)

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.