Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation

• URL: http://arxiv.org/abs/2604.23399v2
• Date: Mon, 04 May 2026 11:59:38 GMT
• Title: Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation
• Abstract summary: DGM-Net is an efficient architecture that improves modeling capability through structural design rather than increasing model capacity.<n>We introduce Directional Geometric Mamba (G-Mamba), a linear-complexity O(N) operator as an alternative to conventional context modeling modules.<n>DGM-Net achieves 80.8% mIoU within 28k iterations, 82.3% mIoU on Cityscapes test set, and 45.24% mIoU on ADE20K.
• Score: 0.30786914102688595
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-performance semantic segmentation has achieved significant progress in recent years, often driven by increasingly large backbones and higher computational budgets. While effective, such approaches introduce substantial computational overhead and limit accessibility under constrained hardware settings. In this paper, we propose DGM-Net (Directional Geometric Mamba Network), an efficient architecture that improves modeling capability through structural design rather than increasing model capacity. We introduce Directional Geometric Mamba (G-Mamba), a linear-complexity O(N) operator as an alternative to conventional context modeling modules such as ASPP and PPM. To further enhance structural awareness in state space model (SSM)-based modeling, we design the DGM-Module, which extracts centripetal flow fields and topological skeletons to guide the scanning process and improve boundary preservation. Without relying on large-scale pretraining or heavy backbone scaling, DGM-Net achieves 80.8% mIoU within 28k iterations, 82.3% mIoU on Cityscapes test set, and 45.24% mIoU on ADE20K. In addition, the model maintains stable performance under constrained hardware settings (e.g., batch size of 2 on 8GB VRAM), highlighting its efficiency and practicality. These results demonstrate that incorporating geometric guidance into SSM-based architectures provides an effective and resource-efficient direction for semantic segmentation.

Related papers

• MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models [55.732137666068446]
  Universal multimodal embedding (UME) increasingly demands encoder's capacity for handling a broad range of tasks and modalities.<n>MoEMB scales UME along the expert axis through mixture-of-experts (MoE)<n>MoEMB surpasses TTE-based methods with >4x active parameters, using significantly less computes.
  arXiv  Detail & Related papers  (2026-09-08T12:29:50Z)
• Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts [13.835014453826057]
  We develop MOSAIC, which formulates model architecture and systems co-design.<n>We instantiate the framework for sparse Mixture-of-Experts (MoE) language models.<n>We show that, within the calibrated sparsity range, an efficiency-agnostic model-FLOPs budget admits no interior optimal sparsity.
  arXiv  Detail & Related papers  (2026-08-11T07:49:00Z)
• BuildMamba: A Visual State-Space Based Model for Multi-Task Building Segmentation and Height Estimation from Satellite Images [0.6773121102591491]
  BuildMamba is a unified multi-task framework designed to exploit the linear-time global modeling of visual state-space models.<n>It achieves an IoU of 0.93 and RMSE of 1.77m on DFC23 benchmark, surpassing state-of-the-art by 0.82m in height estimation.
  arXiv  Detail & Related papers  (2026-03-09T15:56:42Z)
• PerfMamba: Performance Analysis and Pruning of Selective State Space Models [10.047668792033033]
  We study Mamba-1 and Mamba-2 to assess the design principles that contribute to their efficiency in state-space modeling.<n>We propose a pruning technique that removes low-activity states within the SSM component, achieving measurable throughput and memory gains.<n>This approach results in performance improvements across varying sequence lengths, achieving a 1.14x speedup and reducing memory usage by 11.50%.
  arXiv  Detail & Related papers  (2025-11-28T03:09:15Z)
• The Curious Case of In-Training Compression of State Space Models [49.819321766705514]
  State Space Models (SSMs) tackle long sequence modeling tasks efficiently, offer both parallelizable training and fast inference.<n>Key design challenge is striking the right balance between maximizing expressivity and limiting this computational burden.<n>Our approach, textscCompreSSM, applies to Linear Time-Invariant SSMs such as Linear Recurrent Units, but is also extendable to selective models.
  arXiv  Detail & Related papers  (2025-10-03T09:02:33Z)
• Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection [88.47928738482719]
  Linear State Space Models (SSMs) offer remarkable performance gains in sequence modeling.<n>Recent advances, such as Mamba, further enhance SSMs with input-dependent gating and hardware-aware implementations.<n>We introduce Routing Mamba (RoM), a novel approach that scales SSM parameters using sparse mixtures of linear projection experts.
  arXiv  Detail & Related papers  (2025-06-22T19:26:55Z)
• Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution [88.20464308588889]
  We propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR.<n>This method is designed through unfolding an SR optimization function constrained by structural similarity.<n>Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption.
  arXiv  Detail & Related papers  (2025-06-13T14:29:40Z)
• MTGR: Industrial-Scale Generative Recommendation Framework in Meituan [32.12374665716164]
  We propose MTGR (Meituan Generative Recommendation) to address this issue.<n> MTGR achieves training and inference acceleration through user-level compression to ensure efficient scaling.<n>This breakthrough was successfully deployed on Meituan, the world's largest food delivery platform.
  arXiv  Detail & Related papers  (2025-05-24T11:47:28Z)
• Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments [6.908972852063454]
  State-space models (SSMs) have emerged as powerful alternatives to Transformers for sequence modeling.<n>We propose a novel unstructured pruning framework tailored for Mamba models that achieves up to 70% parameter reduction while retaining over 95% of the original performance.
  arXiv  Detail & Related papers  (2025-05-13T07:23:08Z)
• EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference [49.94169109038806]
  This paper introduces EPS-MoE, a novel expert pipeline scheduler for MoE that surpasses the existing parallelism schemes.<n>Our results demonstrate at most 52.4% improvement in prefill throughput compared to existing parallel inference methods.
  arXiv  Detail & Related papers  (2024-10-16T05:17:49Z)
• Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation [60.80423207808076]
  Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation.<n>We propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations.<n>We build HRVMamba, a novel model for efficient high-resolution representation learning.
  arXiv  Detail & Related papers  (2024-10-04T06:19:29Z)
• Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecture [68.13678918660872]
  We design a more capable parameter-sharing architecture based on matrix product operator (MPO) MPO decomposition can reorganize and factorize the information of a parameter matrix into two parts. Our architecture shares the central tensor across all layers for reducing the model size.
  arXiv  Detail & Related papers  (2023-03-27T02:34:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.