# Deformable Mamba for Wide Field of View Segmentation

arXiv: https://arxiv.org/abs/2411.16481 · HTML: https://mlsanity.com/paper/2411.16481/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 60 of its 73 references that are in the map.
- First posted on arXiv 25 Nov 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/)

## Builds on (most cited first, 30 of 60)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)

## Built on by (most cited first, 7 of 7)

- [OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation](https://mlsanity.com/paper/2503.07098/) (2025)
- [Scene-agnostic Pose Regression for Visual Localization](https://mlsanity.com/paper/2503.19543/) (2025)
- [More than the Sum: Panorama-Language Models for Adverse Omni-Scenes](https://mlsanity.com/paper/2603.09573/) (2026)
- [RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization](https://mlsanity.com/paper/2603.27758/) (2026)
- [Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling](https://mlsanity.com/paper/2606.27745/) (2026)
- [SeqLoc: Beyond the Single Frame for Cross-View Geo-Localization in Feature-Sparse Scenes](https://mlsanity.com/paper/2608.07835/) (2026)
- [DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery Localization](https://mlsanity.com/paper/2603.04882/) (2026)

## Abstract (arXiv)

Recent advancements in the Mamba architecture, with its linear computational complexity, being a promising alternative to transformer architectures suffering from quadratic complexity. While existing works primarily focus on adapting Mamba as vision encoders, the critical role of task-specific Mamba decoders remains under-explored, particularly for distortion-prone dense prediction tasks. This paper addresses two interconnected challenges: (1) The design of a Mamba-based decoder that seamlessly adapts to various architectures (e.g., CNN-, Transformer-, and Mamba-based backbones), and (2) The performance degradation in decoders lacking distortion-aware capability when processing wide-FoV images (e.g., 180deg fisheye and 360deg panoramic settings). We propose the Deformable Mamba Decoder, an efficient distortion-aware decoder that integrates Mamba's computational efficiency with adaptive distortion awareness. Comprehensive experiments on five wide-FoV segmentation benchmarks validate its effectiveness. Notably, our decoder achieves a +2.5% performance improvement on the 360deg Stanford2D3D segmentation benchmark while reducing 72% parameters and 97% FLOPs, as compared to the widely-used decoder heads.