mlsanityData to 7 Oct 2026

CCNet: Criss-Cross Attention for Semantic Segmentation

arXiv 1811.11721 ↗First posted 28 Nov 2018cs.CVcited by 717

Not on the map. Why?

Abstract (arXiv)

Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85% of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9%, 45.76% and 55.47% on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at urlhttps://github.com/speedinghzl/CCNet.

Key facts. Cited by 717 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 212; 2022: 185; 2023: 143; 2024: 92; 2025: 50; 2026: 35.

717 papers.

Sort:

By area:

  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  2. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  3. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  4. 2021ViViT: A Video Vision Transformercited by 1,610
  5. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  6. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  7. 2021Transformers in Vision: A Surveycited by 1,009
  8. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  9. 2021Multi-Stage Progressive Image Restorationcited by 813
  10. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 770
  11. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  12. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
38 more
  1. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  2. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  3. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  4. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  5. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  6. 2023GNOT: A General Neural Operator Transformer for Operator Learningcited by 321
  7. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 319
  8. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  9. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  10. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 261
  11. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  12. 2021Incorporating Convolution Designs into Visual Transformerscited by 248
  13. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  14. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  15. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  16. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 229
  17. 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 223
  18. 2022Visual Attention Networkcited by 210
  19. 2022Transformer Quality in Linear Timecited by 189
  20. 2024CBraMod: A Criss-Cross Brain Foundation Model for EEG Decodingcited by 188
  21. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 186
  22. 2021UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagerycited by 166
  23. 2021VOLO: Vision Outlooker for Visual Recognitioncited by 164
  24. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  25. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  26. 2023BiFormer: Vision Transformer with Bi-Level Routing Attentioncited by 150
  27. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  28. 2021Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videoscited by 139
  29. 2022Stripformer: Strip Transformer for Fast Image Deblurringcited by 139
  30. 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
  31. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  32. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  33. 2021DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentationcited by 126
  34. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  35. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  36. 2022Diffusion Probabilistic Model Made Slimcited by 121
  37. 2021Generative Adversarial Transformerscited by 120
  38. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120

50 most cited of 717 All 717 (JSON)