mlsanityData to 7 Oct 2026

Optimized Unet with Attention Mechanism for Multi-Scale Semantic Segmentation

arXiv 2502.03813 ↗First posted 6 Feb 2025cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation is one of the core tasks in the field of computer vision, and its goal is to accurately classify each pixel in an image. The traditional Unet model achieves efficient feature extraction and fusion through an encoder-decoder structure, but it still has certain limitations when dealing with complex backgrounds, long-distance dependencies, and multi-scale targets. To this end, this paper proposes an improved Unet model combined with an attention mechanism, introduces channel attention and spatial attention modules, enhances the model's ability to focus on important features, and optimizes skip connections through a multi-scale feature fusion strategy, thereby improving the combination of global semantic information and fine-grained features. The experiment is based on the Cityscapes dataset and compared with classic models such as FCN, SegNet, DeepLabv3+, and PSPNet. The improved model performs well in terms of mIoU and pixel accuracy (PA), reaching 76.5% and 95.3% respectively. The experimental results verify the superiority of this method in dealing with complex scenes and blurred target boundaries. In addition, this paper discusses the potential of the improved model in practical applications and future expansion directions, indicating that it has broad application value in fields such as autonomous driving, remote sensing image analysis, and medical image processing.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 11 of its 18 references that are in the map. First posted on arXiv 6 Feb 2025.

Builds on

11 of 18 references.

References · 11

  1. 2024Survival Prediction Across Diverse Cancer Types Using Neural Networkscited by 80
  2. 2025Object Detection for Medical Image Analysis: Insights from the RT-DETR Modelcited by 10
  3. 2024Machine Learning Techniques for Pattern Recognition in High-Dimensional Data Miningcited by 8
  4. 2024Accurate Medical Named Entity Recognition Through Specialized NLP Modelscited by 7
  5. 2024Segmenting Medical Images: From UNet to Res-UNet and nnUNetcited by 6
  6. 2024Dynamic Scheduling Strategies for Resource Optimization in Computing Environmentscited by 6
  7. 2024Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Modelscited by 5
  8. 2025Multi-Level Attention and Contrastive Learning for Enhanced Text Classification with an Optimized Transformercited by 5
  9. 2024Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Taskscited by 4
  10. 2024Computer Vision-Driven Gesture Recognition: Toward Natural and Intuitive Human-Computercited by 3
  11. 2024Deep Learning in Image Classification: Evaluating VGG19's Performance on Complex Visual Datacited by 3

Built on by

Cited by year

Citing papers per year: 2025: 9.

9 papers.

  1. 2025Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaborationcited by 9
  2. 2025Context-Aware Rule Mining Using a Dynamic Transformer-Based Frameworkcited by 7
  3. 2025Contrastive and Variational Approaches in Self-Supervised Learning for Complex Data Miningcited by 6
  4. 2025Semantic and Contextual Modeling for Malicious Comment Detection with BERT-BiLSTMcited by 5
  5. 2025Pre-trained Language Models and Few-shot Learning for Medical Entity Extractioncited by 4
  6. 2025A Deep Learning Framework for Boundary-Aware Semantic Segmentationcited by 2
  7. 2025Intelligent Task Scheduling for Microservices via A3C-Based Reinforcement Learningcited by 2
  8. 2025Adaptive Transformer Attention and Multi-Scale Fusion for Spine 3D Segmentationcited by 1
  9. 2025Operational Change Detection for Geographical Information: Overview and Challengescited by 0