mlsanityData to 7 Oct 2026

A Unified Efficient Pyramid Transformer for Semantic Segmentation

arXiv 2107.14209 ↗First posted 29 Jul 2021cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation is a challenging problem due to difficulties in modeling context in complex scenes and class confusions along boundaries. Most literature either focuses on context modeling or boundary refinement, which is less generalizable in open-world scenarios. In this work, we advocate a unified framework(UN-EPT) to segment objects by considering both context information and boundary artifacts. We first adapt a sparse sampling strategy to incorporate the transformer-based attention mechanism for efficient context modeling. In addition, a separate spatial branch is introduced to capture image details for boundary refinement. The whole model can be trained in an end-to-end manner. We demonstrate promising performance on three popular benchmarks for semantic segmentation with low memory footprint. Code will be released soon.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 69 of its 79 references that are in the map. First posted on arXiv 29 Jul 2021.

Builds on

69 of 79 references.

References · 69

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  9. 2017Squeeze-and-Excitation Networkscited by 4,763
  10. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  11. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
38 more
  1. 2020Longformer: The Long-Document Transformercited by 3,362
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  3. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  5. 2016Pyramid Scene Parsing Networkcited by 2,472
  6. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  7. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  8. 2020Reformer: The Efficient Transformercited by 1,658
  9. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  10. 2015Spatial Transformer Networkscited by 1,423
  11. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  12. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  13. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  14. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  15. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  16. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  17. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  18. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  19. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  20. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  21. 2020ResNeSt: Split-Attention Networkscited by 445
  22. 2019PointRend: Image Segmentation as Renderingcited by 439
  23. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  24. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  25. 2018Context Encoding for Semantic Segmentationcited by 289
  26. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  27. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  28. 2015ParseNet: Looking Wider to See Bettercited by 176
  29. 2019Gated-SCNN: Gated Shape CNNs for Semantic Segmentationcited by 165
  30. 2020Multiscale Deep Equilibrium Modelscited by 149
  31. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  32. 2016Richer Convolutional Features for Edge Detectioncited by 141
  33. 2018OCNet: Object Context Network for Scene Parsingcited by 140
  34. 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
  35. 2020Disentangled Non-Local Neural Networkscited by 132
  36. 2020Context Prior for Scene Segmentationcited by 121
  37. 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
  38. 2019Boundary-Aware Feature Propagation for Scene Segmentationcited by 107

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 6; 2023: 3; 2024: 3; 2025: 1.

14 papers.

Sort:

  1. 2022ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentationcited by 178
  2. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  3. 2023DilateFormer: Multi-Scale Dilated Transformer for Visual Recognitioncited by 34
  4. 2023CLUSTSEG: Clustering for Universal Segmentationcited by 32
  5. 2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
  6. 2022NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Nightcited by 21
  7. 2024Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentationcited by 21
  8. 2021Blending Anti-Aliasing into Vision Transformercited by 16
  9. 2022Centralized Feature Pyramid for Object Detectioncited by 13
  10. 2024MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selectioncited by 12
  11. 2022Pyramid Fusion Transformer for Semantic Segmentationcited by 6
  12. 2024Attacking Transformers with Feature Diversity Adversarial Perturbationcited by 3
2 more
  1. 2025TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularizationcited by 1
  2. 2023Class Enhancement Losses with Pseudo Labels for Zero-shot Semantic Segmentationcited by 0