# UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken arXiv: https://arxiv.org/abs/2508.00421 ยท HTML: https://mlsanity.com/paper/2508.00421/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Placed in Mamba for image restoration, one of 10 directions in State-space sequence models (S4, Mamba). - Builds on 29 of its 60 references that are in the map. - First posted on arXiv 1 Aug 2025. ## Placed in - State-space sequence models (S4, Mamba) / [Mamba for image restoration](https://mlsanity.com/ssm/mamba-for-image-restoration/) ## Builds on (most cited first, 29 of 29) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014) - [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021) - [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017) - [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023) - [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021) - [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021) - [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017) - [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017) - [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018) - [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021) - [Hungry Hungry Hippos: Towards Language Modeling with State Space Models](https://mlsanity.com/paper/2212.14052/) (2022) - [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019) - [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019) - [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019) - [LocalMamba: Visual State Space Model with Windowed Selective Scan](https://mlsanity.com/paper/2403.09338/) (2024) - [RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model](https://mlsanity.com/paper/2306.16269/) (2023) - [PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition](https://mlsanity.com/paper/2403.17695/) (2024) - [Boundary-preserving Mask R-CNN](https://mlsanity.com/paper/2007.08921/) (2020) - [Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2404.04256/) (2024) - [Mask Transfiner for High-Quality Instance Segmentation](https://mlsanity.com/paper/2111.13673/) (2021) - [PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators](https://mlsanity.com/paper/2306.08918/) (2023) - [Advances in Deep Concealed Scene Understanding](https://mlsanity.com/paper/2304.11234/) (2023) - [Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion](https://mlsanity.com/paper/2410.15091/) (2024) - [Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset](https://mlsanity.com/paper/2406.06039/) (2024) - [S4Net: Single Stage Salient-Instance Segmentation](https://mlsanity.com/paper/1711.07618/) (2017) - [Regularized Densely-connected Pyramid Network for Salient Instance Segmentation](https://mlsanity.com/paper/2008.12416/) (2020) - [Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing](https://mlsanity.com/paper/2104.01329/) (2021) ## Built on by (most cited first, 7 of 7) - [Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter](https://mlsanity.com/paper/2511.08334/) (2025) - [RDNet: Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network in Optical Remote Sensing Images](https://mlsanity.com/paper/2603.12215/) (2026) - [G2HFNet: GeoGran-Aware Hierarchical Feature Fusion Network for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/2603.12680/) (2026) - [RSONet: Region-guided Selective Optimization Network for RGB-T Salient Object Detection](https://mlsanity.com/paper/2603.12685/) (2026) - [UniV2D: Bridging Visual Restoration and Semantic Perception for Underwater Salient Object Detection](https://mlsanity.com/paper/2605.07146/) (2026) - [CoRef-DETR: Decoupled Global Context and Selective Boundary-Category Refinement for Underwater Instance Segmentation](https://mlsanity.com/paper/2606.08002/) (2026) - [Degradation-Guided Underwater Image Restoration with Task-Oriented Latent Control](https://mlsanity.com/paper/2608.08661/) (2026) ## Abstract (arXiv) Underwater Instance Segmentation (UIS) tasks are crucial for underwater complex scene detection. Mamba, as an emerging state space model with inherently linear complexity and global receptive fields, is highly suitable for processing image segmentation tasks with long sequence features. However, due to the particularity of underwater scenes, there are many challenges in applying Mamba to UIS. The existing fixed-patch scanning mechanism cannot maintain the internal continuity of scanned instances in the presence of severely underwater color distortion and blurred instance boundaries, and the hidden state of the complex underwater background can also inhibit the understanding of instance objects. In this work, we propose the first Mamba-based underwater instance segmentation model UIS-Mamba, and design two innovative modules, Dynamic Tree Scan (DTS) and Hidden State Weaken (HSW), to migrate Mamba to the underwater task. DTS module maintains the continuity of the internal features of the instance objects by allowing the patches to dynamically offset and scale, thereby guiding the minimum spanning tree and providing dynamic local receptive fields. HSW module suppresses the interference of complex backgrounds and effectively focuses the information flow of state propagation to the instances themselves through the Ncut-based hidden state weakening mechanism. Experimental results show that UIS-Mamba achieves state-of-the-art performance on both UIIS and USIS10K datasets, while maintaining a low number of parameters and computational complexity. Code is available at https://github.com/Maricalce/UIS-Mamba.