Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment

• URL: http://arxiv.org/abs/2508.08811v1
• Date: Tue, 12 Aug 2025 10:10:10 GMT
• Title: Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment
• Authors: Shi-Chen Zhang, Yunheng Li, Yu-Huan Wu, Qibin Hou, Ming-Ming Cheng,
• Abstract summary: We propose a dual-branch offset learning paradigm that learns feature and class offsets to dynamically refine both class representations and spatial image features.<n>Based on the proposed paradigm, we construct an efficient semantic segmentation network, OffSeg.<n>Experiments on four datasets, including ADE20K, Cityscapes, COCO-Stuff-164K, and Pascal Context, demonstrate consistent improvements with negligible parameters.
• Score: 67.94226713255732
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference through lightweight designs, we reveal their inherent limitation: misalignment between class representations and image features caused by a per-pixel classification paradigm. With experimental analysis, we find that this paradigm results in a highly challenging assumption for efficient scenarios: Image pixel features should not vary for the same category in different images. To address this dilemma, we propose a coupled dual-branch offset learning paradigm that explicitly learns feature and class offsets to dynamically refine both class representations and spatial image features. Based on the proposed paradigm, we construct an efficient semantic segmentation network, OffSeg. Notably, the offset learning paradigm can be adopted to existing methods with no additional architectural changes. Extensive experiments on four datasets, including ADE20K, Cityscapes, COCO-Stuff-164K, and Pascal Context, demonstrate consistent improvements with negligible parameters. For instance, on the ADE20K dataset, our proposed offset learning paradigm improves SegFormer-B0, SegNeXt-T, and Mask2Former-Tiny by 2.7%, 1.9%, and 2.6% mIoU, respectively, with only 0.1-0.2M additional parameters required.

Related papers

• SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation [11.176993272867396]
  In this paper, we propose a novel Semantic and Spatial Adaptive (SSA-Seg) to address the challenges of semantic segmentation. Specifically, we employ the coarse masks obtained from the fixed prototypes as a guide to adjust the fixed prototype towards the center of the semantic and spatial domains in the test image. Results show that the proposed SSA-Seg significantly improves the segmentation performance of the baseline models with only a minimal increase in computational cost.
  arXiv  Detail & Related papers  (2024-05-10T15:14:23Z)
• Learning Invariant Inter-pixel Correlations for Superpixel Generation [12.605604620139497]
  Learnable features exhibit constrained discriminative capability, resulting in unsatisfactory pixel grouping performance. We propose the Content Disentangle Superpixel algorithm to selectively separate the invariant inter-pixel correlations and statistical properties. The experimental results on four benchmark datasets demonstrate the superiority of our approach to existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-28T09:46:56Z)
• ClusterFormer: Clustering As A Universal Visual Learner [80.79669078819562]
  CLUSTERFORMER is a universal vision model based on the CLUSTERing paradigm with TransFORMER. It is capable of tackling heterogeneous vision tasks with varying levels of clustering granularity. For its efficacy, we hope our work can catalyze a paradigm shift in universal models in computer vision.
  arXiv  Detail & Related papers  (2023-09-22T22:12:30Z)
• Target-aware Bi-Transformer for Few-shot Segmentation [4.3753381458828695]
  Few-shot semantic segmentation (FSS) aims to use limited labeled support images to identify the segmentation of new classes of objects. In this paper, we propose the Target-aware Bi-Transformer Network (TBTNet) to equivalent treat of support images and query image. A vigorous Target-aware Transformer Layer (TTL) also be designed to distill correlations and force the model to focus on foreground information.
  arXiv  Detail & Related papers  (2023-09-18T05:28:51Z)
• MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation [110.09800389100599]
  We propose MixReorg, a novel and straightforward pre-training paradigm for semantic segmentation. Our approach involves generating fine-grained patch-text pairs data by mixing image patches while preserving the correspondence between patches and text. With MixReorg as a mask learner, conventional text-supervised semantic segmentation models can achieve highly generalizable pixel-semantic alignment ability.
  arXiv  Detail & Related papers  (2023-08-09T09:35:16Z)
• Improving Human-Object Interaction Detection via Virtual Image Learning [68.56682347374422]
  Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects. In this paper, we propose to alleviate the impact of such an unbalanced distribution via Virtual Image Leaning (VIL) A novel label-to-image approach, Multiple Steps Image Creation (MUSIC), is proposed to create a high-quality dataset that has a consistent distribution with real images.
  arXiv  Detail & Related papers  (2023-08-04T10:28:48Z)
• Searching a Compact Architecture for Robust Multi-Exposure Image Fusion [55.37210629454589]
  Two major stumbling blocks hinder the development, including pixel misalignment and inefficient inference. This study introduces an architecture search-based paradigm incorporating self-alignment and detail repletion modules for robust multi-exposure image fusion. The proposed method outperforms various competitive schemes, achieving a noteworthy 3.19% improvement in PSNR for general scenarios and an impressive 23.5% enhancement in misaligned scenarios.
  arXiv  Detail & Related papers  (2023-05-20T17:01:52Z)
• Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning [116.91819311885166]
  We propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to textbfCross-samples and Multi-level representation. Our method, termed as CsMl, has the ability to integrate multi-level visual representations across samples in a robust way.
  arXiv  Detail & Related papers  (2020-12-04T17:26:24Z)
• Dense Contrastive Learning for Self-Supervised Visual Pre-Training [102.15325936477362]
  We present dense contrastive learning, which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images. Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only 1% slower)
  arXiv  Detail & Related papers  (2020-11-18T08:42:32Z)

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.