mlsanityData to 14 Oct 2026

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

arXiv 1412.7062 ↗First posted 22 Dec 2014cs.CV cs.LG cs.NEcited by 554

Not on the map. Why?

Abstract (arXiv)

Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "semantic image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Qualitatively, our "DeepLab" system is able to localize segment boundaries at a level of accuracy which is beyond previous methods. Quantitatively, our method sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 71.6% IOU accuracy in the test set. We show how these results can be obtained efficiently: Careful network re-purposing and a novel application of the 'hole' algorithm from the wavelet community allow dense computation of neural net responses at 8 frames per second on a modern GPU.

Key facts. Cited by 554 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 164; 2022: 123; 2023: 115; 2024: 85; 2025: 55; 2026: 11.

554 papers.

Sort:

By area:

  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  2. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  3. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  4. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 328
  5. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  6. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 320
  7. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  8. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  9. 2021Coordinate Attention for Efficient Mobile Network Designcited by 241
  10. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  11. 2022Visual Attention Networkcited by 210
  12. 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 201
38 more
  1. 2022ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentationcited by 178
  2. 2021UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagerycited by 167
  3. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  4. 2022SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentationcited by 164
  5. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  6. 2022Semantic Image Synthesis via Diffusion Modelscited by 132
  7. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  8. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  9. 2021Are Large-scale Datasets Necessary for Self-Supervised Pre-training?cited by 117
  10. 2022ReSTR: Convolution-free Referring Image Segmentation Using Transformerscited by 112
  11. 2023Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentationcited by 112
  12. 2021Cross-Modal Progressive Comprehension for Referring Segmentationcited by 102
  13. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  14. 2022HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentationcited by 95
  15. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  16. 2021CAT: Cross Attention in Vision Transformercited by 92
  17. 2021Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationcited by 92
  18. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  19. 2021Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenescited by 89
  20. 2022Rethinking Efficient Lane Detection via Curve Modelingcited by 88
  21. 2021Face Forensics in the Wildcited by 87
  22. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  23. 2022PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllerscited by 84
  24. 2022Semantic-Aware Domain Generalized Segmentationcited by 79
  25. 2021Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentationcited by 77
  26. 2021Topology-Aware Segmentation Using Discrete Morse Theorycited by 75
  27. 2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
  28. 2021STEP: Segmenting and Tracking Every Pixelcited by 73
  29. 2022Cross Language Image Matching for Weakly Supervised Semantic Segmentationcited by 72
  30. 2021Context Decoupling Augmentation for Weakly Supervised Semantic Segmentationcited by 69
  31. 2023CLIP as RNN: Segment Countless Visual Concepts without Training Endeavorcited by 69
  32. 2021Lite Vision Transformer with Enhanced Self-Attentioncited by 64
  33. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64
  34. 2023Zero-shot spatial layout conditioning for text-to-image diffusion modelscited by 64
  35. 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 62
  36. 2022CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentationcited by 60
  37. 2024SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and Morecited by 60
  38. 2022Waymo Open Dataset: Panoramic Video Panoptic Segmentationcited by 58

50 most cited of 554 All 554 (JSON)