MSCA-UNet: Multi-Scale Context and Attention U-Net for Image Segmentation

• URL: http://arxiv.org/abs/2609.06356v1
• Date: Sun, 06 Sep 2026 03:16:51 GMT
• Title: MSCA-UNet: Multi-Scale Context and Attention U-Net for Image Segmentation
• Abstract summary: MSCA-UNet is a U-Net-based segmentation architecture that combines multi-scale contextual aggregation at the bottleneck with channel-spatial attention refinement in the decoder.<n>Under identical experimental settings, the baseline U-Net achieves 96.9% mIoU on a held-out test set.<n>The results support the view that multi-scale context enrichment and attention-based feature refinement provide complementary benefits within a U-Net framework.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: U-Net remains a practical baseline for image segmentation because of its simple encoder-decoder structure and skip connections. However, the bottleneck representation is still dominated by a limited set of receptive fields, while decoder features are propagated without explicitly emphasizing the most informative channels and spatial locations. This paper presents MSCA-UNet, a U-Net-based segmentation architecture that combines multi-scale contextual aggregation at the bottleneck with channel-spatial attention refinement in the decoder. The multi-scale module uses parallel atrous convolutions to capture contextual features at different receptive fields, while Convolutional Block Attention Modules (CBAMs) progressively recalibrate decoder features. Under identical experimental settings, the baseline U-Net achieves 96.9% mIoU on a held-out test set. Adding multi-scale context improves mIoU to 97.5%, while attention alone reaches 98.4%. Combining both mechanisms yields 99.1% mIoU, a 2.2 percentage-point improvement over the baseline. Parameter analysis further shows that the attention-only variant adds approximately 0.044M parameters, whereas the multi-scale module contributes most of the additional model capacity. The results support the view that multi-scale context enrichment and attention-based feature refinement provide complementary benefits within a U-Net framework.

Related papers

• CI-ICM: Channel Importance-driven Learned Image Coding for Machines [56.1188469769241]
  We propose a Channel Importance-driven learned Image Coding for Machines (CI-ICM) to maximize the performance of machine vision tasks.<n>The proposed CI-ICM achieves BD-mAP@50:95 gains of 16.25%$ in object detection and 13.72%$ in instance segmentation over the established baseline.
  arXiv  Detail & Related papers  (2026-04-07T02:36:47Z)
• MSA2-Net: Utilizing Self-Adaptive Convolution Module to Extract Multi-Scale Information in Medical Image Segmentation [31.007198872745892]
  Self-Adaptive Convolution Module dynamically adjusts the size of the convolution kernels depending on unique fingerprints of different datasets.<n> Module is strategically integrated into two key components of the MSA2-Net: the Multi-Scale Convolution Bridge and the Multi-Scale Amalgamation Decoder.
  arXiv  Detail & Related papers  (2025-09-01T14:19:15Z)
• Multi-view Aggregation Network for Dichotomous Image Segmentation [76.75904424539543]
  Dichotomous Image (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images. Existing methods rely on tedious multiple encoder-decoder streams and stages to gradually complete the global localization and local refinement. Inspired by it, we model DIS as a multi-view object perception problem and provide a parsimonious multi-view aggregation network (MVANet) Experiments on the popular DIS-5K dataset show that our MVANet significantly outperforms state-of-the-art methods in both accuracy and speed.
  arXiv  Detail & Related papers  (2024-04-11T03:00:00Z)
• MFPNet: Multi-scale Feature Propagation Network For Lightweight Semantic Segmentation [5.58363644107113]
  We propose a novel lightweight segmentation architecture, called Multi-scale Feature Propagation Network (Net) We design a robust-Decoder structure featuring symmetrical residual blocks that consist of flexible bottleneck residual modules (BRMs) Taking benefit of their capacity to model latent long-range contextual relationships, we leverage Graph Convolutional Networks (GCNs) to facilitate multiscale feature propagation between the BRM blocks.
  arXiv  Detail & Related papers  (2023-09-10T02:02:29Z)
• Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation [48.995367430746086]
  High-accuracy Dichotomous Image rendering (DIS) aims to pinpoint category-agnostic foreground objects from natural scenes. We introduce a novel Unite-Divide-Unite Network (UDUN) that restructures and bipartitely arranges complementary features to boost the effectiveness of trunk and structure identification. Using 1024*1024 input, our model enables real-time inference at 65.3 fps with ResNet-18.
  arXiv  Detail & Related papers  (2023-07-26T09:04:35Z)
• Efficient Multi-Scale Attention Module with Cross-Spatial Learning [4.046170185945849]
  A novel efficient multi-scale attention (EMA) module is proposed. We focus on retaining the information on per channel and decreasing the computational overhead. We conduct extensive ablation studies and experiments on image classification and object detection tasks.
  arXiv  Detail & Related papers  (2023-05-23T00:35:47Z)
• Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training [88.80694147730883]
  We investigate a variety of Modality-Shared Contrastive Language-Image Pre-training (MS-CLIP) frameworks. In studied conditions, we observe that a mostly unified encoder for vision and language signals outperforms all other variations that separate more parameters. Our approach outperforms vanilla CLIP by 1.6 points in linear probing on a collection of 24 downstream vision tasks.
  arXiv  Detail & Related papers  (2022-07-26T05:19:16Z)
• Specificity-preserving RGB-D Saliency Detection [103.3722116992476]
  We propose a specificity-preserving network (SP-Net) for RGB-D saliency detection. Two modality-specific networks and a shared learning network are adopted to generate individual and shared saliency maps. Experiments on six benchmark datasets demonstrate that our SP-Net outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-18T14:14:22Z)
• Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation [87.01669173673288]
  We propose an encoder fusion network (EFN), which transforms the visual encoder into a multi-modal feature learning network. A co-attention mechanism is embedded in the EFN to realize the parallel update of multi-modal features. The experiment results on four benchmark datasets demonstrate that the proposed approach achieves the state-of-the-art performance without any post-processing.
  arXiv  Detail & Related papers  (2021-05-05T02:27:25Z)
• MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images [11.047174552053626]
  MACU-Net is a multi-scale skip connected and asymmetric-convolution-based U-Net for fine-resolution remotely sensed images. Our design has the following advantages: (1) The multi-scale skip connections combine and realign semantic features contained in both low-level and high-level feature maps; (2) the asymmetric convolution block strengthens the feature representation and feature extraction capability of a standard convolution layer. Experiments conducted on two remotely sensed datasets demonstrate that the proposed MACU-Net transcends the U-Net, U-NetPPL, U-Net 3+, amongst other benchmark approaches.
  arXiv  Detail & Related papers  (2020-07-26T08:56:47Z)
• Distance Guided Channel Weighting for Semantic Segmentation [4.10724123131976]
  We introduce Distance Guided Channel Weighting Module (DGCW) The DGCW module is constructed in a pixel-wise context extraction manner. We propose the Distance Guided Channel Weighting Network (DGCWNet)
  arXiv  Detail & Related papers  (2020-04-27T09:57:12Z)

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.