mlsanityData to 7 Oct 2026

SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

arXiv 2209.08575 ↗First posted 18 Sep 2022cs.CVcited by 252

Not on the map. Why?

Abstract (arXiv)

We present SegNeXt, a simple convolutional network architecture for semantic segmentation. Recent transformer-based models have dominated the field of semantic segmentation due to the efficiency of self-attention in encoding spatial information. In this paper, we show that convolutional attention is a more efficient and effective way to encode contextual information than the self-attention mechanism in transformers. By re-examining the characteristics owned by successful segmentation models, we discover several key components leading to the performance improvement of segmentation models. This motivates us to design a novel convolutional attention network that uses cheap convolutional operations. Without bells and whistles, our SegNeXt significantly improves the performance of previous state-of-the-art methods on popular benchmarks, including ADE20K, Cityscapes, COCO-Stuff, Pascal VOC, Pascal Context, and iSAID. Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90.6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it. On average, SegNeXt achieves about 2.0% mIoU improvements compared to the state-of-the-art methods on the ADE20K datasets with the same or fewer computations. Code is available at https://github.com/uyzhang/JSeg (Jittor) and https://github.com/Visual-Attention-Network/SegNeXt (Pytorch).

Key facts. Cited by 252 papers in the map (data through 7 Oct 2026). Builds on 88 of its 99 references that are in the map. First posted on arXiv 18 Sep 2022.

Builds on

88 of 99 references.

References · 88

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  8. 2016Densely Connected Convolutional Networkscited by 6,691
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  10. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  11. 2017Squeeze-and-Excitation Networkscited by 4,763
  12. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
38 more
  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2014Going Deeper with Convolutionscited by 4,231
  3. 2022A ConvNet for the 2020scited by 3,545
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  10. 2017Non-local Neural Networkscited by 2,290
  11. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  12. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  13. 2021Vision Transformers for Dense Predictioncited by 1,789
  14. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  15. 2017Deformable Convolutional Networkscited by 1,481
  16. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  17. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  18. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  19. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  20. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  21. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  22. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  23. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  24. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  25. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  26. 2020PCT: Point cloud transformercited by 730
  27. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  28. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  29. 2019Panoptic Feature Pyramid Networkscited by 644
  30. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  31. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 572
  32. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  33. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  34. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  35. 2020ResNeSt: Split-Attention Networkscited by 445
  36. 2019PointRend: Image Segmentation as Renderingcited by 439
  37. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  38. 2020Rethinking Pre-training and Self-trainingcited by 352

50 most cited of 88 All 88 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 57; 2024: 74; 2025: 70; 2026: 45.

252 papers.

Sort:

By area:

  1. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  2. 2024OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understandingcited by 126
  3. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  4. 2023Delivering Arbitrary-Modal Semantic Segmentationcited by 115
  5. 2023Large Selective Kernel Network for Remote Sensing Object Detectioncited by 98
  6. 2023InceptionNeXt: When Inception Meets ConvNeXtcited by 84
  7. 2022Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognitioncited by 81
  8. 2024OMG-Seg: Is One Model Good Enough For All Segmentation?cited by 73
  9. 2024Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encodingcited by 72
  10. 2023DFormer: Rethinking RGBD Representation Learning for Semantic Segmentationcited by 58
  11. 2024Poly Kernel Inception Network for Remote Sensing Detectioncited by 52
  12. 2024GeoCalib: Learning Single-image Calibration with Geometric Optimizationcited by 50
38 more
  1. 2023Open-Vocabulary Segmentation with Semantic-Assisted Calibrationcited by 49
  2. 2024Frequency-aware Feature Fusion for Dense Image Predictioncited by 48
  3. 2024LSKNet: A Foundation Lightweight Backbone for Remote Sensingcited by 44
  4. 2023CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentationcited by 43
  5. 2023Global Knowledge Calibration for Fast Open-Vocabulary Segmentationcited by 40
  6. 2023Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentationcited by 35
  7. 2023WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfacescited by 34
  8. 2024Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentationcited by 34
  9. 2023YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detectioncited by 33
  10. 2024Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Modelcited by 31
  11. 2024SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentationcited by 31
  12. 2025DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentationcited by 30
  13. 2024LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregationcited by 28
  14. 2024Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentationcited by 25
  15. 2024SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Imagescited by 25
  16. 2024CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attentioncited by 23
  17. 2023SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentationcited by 22
  18. 2024Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentationcited by 21
  19. 2023SANeRF-HQ: Segment Anything for NeRF in High Qualitycited by 20
  20. 2023360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye Viewcited by 18
  21. 2023Single Frame Semantic Segmentation Using Multi-Modal Spherical Imagescited by 18
  22. 2024SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentationcited by 18
  23. 2024AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentationcited by 18
  24. 2023LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoningcited by 17
  25. 2024Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentationcited by 17
  26. 2025RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretationcited by 16
  27. 2023ADNet: Lane Shape Prediction via Anchor Decompositioncited by 14
  28. 2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14
  29. 2024Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentationcited by 14
  30. 2024Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentationcited by 14
  31. 2024PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentationcited by 14
  32. 2025Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detectioncited by 14
  33. 2024Frontiers in Intelligent Colonoscopycited by 13
  34. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  35. 2024U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentationcited by 12
  36. 2024Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenescited by 12
  37. 2024ASPS: Augmented Segment Anything Model for Polyp Segmentationcited by 12
  38. 2024MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentationcited by 12

50 most cited of 252 All 252 (JSON)