mlsanityData to 14 Oct 2026

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

arXiv 1511.00561 ↗First posted 2 Nov 2015cs.CV cs.LG cs.NEcited by 1,487

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer. The architecture of the encoder network is topologically identical to the 13 convolutional layers in the VGG16 network. The role of the decoder network is to map the low resolution encoder feature maps to full input resolution feature maps for pixel-wise classification. The novelty of SegNet lies is in the manner in which the decoder upsamples its lower resolution input feature map(s). Specifically, the decoder uses pooling indices computed in the max-pooling step of the corresponding encoder to perform non-linear upsampling. This eliminates the need for learning to upsample. The upsampled maps are sparse and are then convolved with trainable filters to produce dense feature maps. We compare our proposed architecture with the widely adopted FCN and also with the well known DeepLab-LargeFOV, DeconvNet architectures. This comparison reveals the memory versus accuracy trade-off involved in achieving good segmentation performance. SegNet was primarily motivated by scene understanding applications. Hence, it is designed to be efficient both in terms of memory and computational time during inference. It is also significantly smaller in the number of trainable parameters than other competing architectures. We also performed a controlled benchmark of SegNet and other architectures on both road scenes and SUN RGB-D indoor scene segmentation tasks. We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures. We also provide a Caffe implementation of SegNet and a web demo at http://mi.eng.cam.ac.uk/projects/segnet/.

Key facts. Cited by 1,487 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 2; 2019: 1; 2020: 0; 2021: 390; 2022: 327; 2023: 282; 2024: 261; 2025: 148; 2026: 76.

1,487 papers.

Sort:

By area:

  1. 2021Vision Transformers for Dense Predictioncited by 1,803
  2. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  3. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  4. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
  5. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 320
  6. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  7. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 280
  8. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 279
  9. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  10. 2023Personalize Segment Anything Model with One Shotcited by 250
  11. 2025Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcementcited by 239
  12. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 231
38 more
  1. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  2. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 215
  3. 2021A Survey of Human-in-the-loop for Machine Learningcited by 215
  4. 2022Multi-Task Learning as a Bargaining Gamecited by 215
  5. 2021Diffusion Models for Implicit Image Segmentation Ensemblescited by 198
  6. 2022Medical Image Segmentation Review: The success of U-Netcited by 191
  7. 2022MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Modelcited by 180
  8. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  9. 2021UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagerycited by 167
  10. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  11. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  12. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  13. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  14. 2022UIU-Net: U-Net in U-Net for Infrared Small Object Detectioncited by 127
  15. 2021DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentationcited by 126
  16. 2021Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bankcited by 125
  17. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  18. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 123
  19. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  20. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  21. 2021Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentationcited by 113
  22. 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
  23. 2023Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentationcited by 112
  24. 2022Highly Accurate Dichotomous Image Segmentationcited by 110
  25. 2022Hyperbolic Image Segmentationcited by 102
  26. 2021Large-scale Unsupervised Semantic Segmentationcited by 101
  27. 2021Locate then Segment: A Strong Pipeline for Referring Image Segmentationcited by 98
  28. 2023SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentationcited by 97
  29. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  30. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  31. 2021Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentationcited by 95
  32. 2022HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentationcited by 95
  33. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  34. 2021Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationcited by 92
  35. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  36. 2021Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenescited by 89
  37. 2021Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentationcited by 88
  38. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87

50 most cited of 1,487 All 1,487 (JSON)