When Simplicity Wins: Bottleneck-Aware Context Modeling for Lightweight Semantic Segmentation

• URL: http://arxiv.org/abs/2608.18979v1
• Date: Wed, 19 Aug 2026 14:47:07 GMT
• Title: When Simplicity Wins: Bottleneck-Aware Context Modeling for Lightweight Semantic Segmentation
• Abstract summary: We propose SiConMo, a lightweight yet effective framework for semantic segmentation.<n>We show that simplicity arises from a key design principle: at very low computational budgets, the bottleneck is the most efficient stage to integrate local and global context.<n> experiments on ADE20K, PASCAL Context, Cityscapes, and COCO-Stuff demonstrate that SiConMo achieves a state-of-the-art accuracy-efficiency trade-off.
• Score: 58.325533783810016
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semantic segmentation demands a careful balance between accuracy, efficiency, and scalability, which remains difficult to achieve for high-resolution imagery. Convolutional networks effectively model local patterns but struggle with long-range dependencies, whereas Vision Transformers capture global context at a high computational cost. While recent work largely focuses on encoder design, the bottleneck stage, central to contextual aggregation and information flow, has been relatively overlooked. We propose SiConMo, a lightweight yet effective framework, implemented in two variants: an RGB-only model (SiConMo) and a GME-enhanced variant (SiConMo$_\dagger$). We show that simplicity arises from a key design principle: at very low computational budgets, the bottleneck is the most efficient stage to integrate local and global context. SiConMo integrates three complementary components: a Token Pyramid Extraction Module for hierarchical multi-scale representation, a Transformer-Branched Depthwise Convolution block for bottleneck-aware context modeling, and a Feature Merging Module that preserves spatial structure while enhancing semantic consistency. Extensive experiments on ADE20K, PASCAL Context, Cityscapes, and COCO-Stuff demonstrate that SiConMo achieves a state-of-the-art accuracy-efficiency trade-off among lightweight semantic segmentation models, highlighting simplicity as a powerful design principle.

Related papers

• MVOFormer: Flow-Semantic Transformer for Robust Monocular Visual Odometry [11.059456227749914]
  MVOFormer is a novel transformer framework for robust monocular visual odometry.<n>MVOFormer achieves superior zero-shot generalization and robustness, significantly outperforming prior learning-based frame-to-frame methods.
  arXiv  Detail & Related papers  (2026-06-15T09:39:28Z)
• MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone Architecture [12.168520751389622]
  Hyperspectral image (HSI) classification faces challenges such as high-dimensional data, limited training samples, and spectral redundancy.<n>This paper proposes a novel MVNet network architecture that integrates 3D-CNN's local feature extraction, Transformer's global modeling, and Mamba's linear sequence modeling capabilities.<n>On IN, UP, and KSC datasets, MVNet outperforms mainstream hyperspectral image classification methods in both classification accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-07-06T14:52:26Z)
• 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)
• LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation [14.20517652381698]
  A single-branch lightweight global modeling network (LGM-Pose) is proposed to address these challenges.<n>In the network, a lightweight MobileViM Block is designed with a proposed Lightweight Attentional Representation Module (LARM)
  arXiv  Detail & Related papers  (2025-06-05T02:29:04Z)
• LeMoRe: Learn More Details for Lightweight Semantic Segmentation [48.81126061219231]
  We introduce an efficient paradigm by synergizing explicit and implicit modeling to balance computational efficiency with representational fidelity.<n>Our method combines well-defined Cartesian directions with explicitly modeled views and implicitly inferred intermediate representations, efficiently capturing global dependencies.
  arXiv  Detail & Related papers  (2025-05-29T04:55:10Z)
• VRS-UIE: Value-Driven Reordering Scanning for Underwater Image Enhancement [104.78586859995333]
  State Space Models (SSMs) have emerged as a promising backbone for vision tasks due to their linear complexity and global receptive field.<n>The predominance of large-portion, homogeneous but useless oceanic backgrounds can dilute the feature representation responses of sparse yet valuable targets.<n>We propose a novel Value-Driven Reordering Scanning framework for Underwater Image Enhancement (UIE)<n>Our framework sets a new state-of-the-art, delivering superior enhancement performance (surpassing WMamba by 0.89 dB on average) by effectively suppressing water bias and preserving structural and color fidelity.
  arXiv  Detail & Related papers  (2025-05-02T12:21:44Z)
• CFMD: Dynamic Cross-layer Feature Fusion for Salient Object Detection [7.262250906929891]
  Cross-layer feature pyramid networks (CFPNs) have achieved notable progress in multi-scale feature fusion and boundary detail preservation for salient object detection.<n>To address these challenges, we propose CFMD, a novel cross-layer feature pyramid network that introduces two key innovations.<n>First, we design a context-aware feature aggregation module (CFLMA), which incorporates the state-of-the-art Mamba architecture to construct a dynamic weight distribution mechanism.<n>Second, we introduce an adaptive dynamic upsampling unit (CFLMD) that preserves spatial details during resolution recovery.
  arXiv  Detail & Related papers  (2025-04-02T03:22:36Z)
• ContextFormer: Redefining Efficiency in Semantic Segmentation [48.81126061219231]
  Convolutional methods, although capturing local dependencies well, struggle with long-range relationships.<n>Vision Transformers (ViTs) excel in global context capture but are hindered by high computational demands.<n>We propose ContextFormer, a hybrid framework leveraging the strengths of CNNs and ViTs in the bottleneck to balance efficiency, accuracy, and robustness for real-time semantic segmentation.
  arXiv  Detail & Related papers  (2025-01-31T16:11:04Z)
• Core Context Aware Transformers for Long Context Language Modeling [50.774702091154204]
  We propose a plug-and-play Core Context Aware (CCA) Attention for efficient long-context modeling.<n>Our method automatically focuses and strengthens core context while diminishing redundancy during the learning process.<n>Our method is able to replace the self-attention module in existing Large Language Models with minimal fine-tuning cost.
  arXiv  Detail & Related papers  (2024-12-17T01:54:08Z)

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.