mlsanityData to 14 Oct 2026

FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation

arXiv 2111.02394 ↗First posted 3 Nov 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

We propose an accurate and efficient scene text detection framework, termed FAST (i.e., faster arbitrarily-shaped text detector). Different from recent advanced text detectors that used complicated post-processing and hand-crafted network architectures, resulting in low inference speed, FAST has two new designs. (1) We design a minimalist kernel representation (only has 1-channel output) to model text with arbitrary shape, as well as a GPU-parallel post-processing to efficiently assemble text lines with a negligible time overhead. (2) We search the network architecture tailored for text detection, leading to more powerful features than most networks that are searched for image classification. Benefiting from these two designs, FAST achieves an excellent trade-off between accuracy and efficiency on several challenging datasets, including Total Text, CTW1500, ICDAR 2015, and MSRA-TD500. For example, FAST-T yields 81.6% F-measure at 152 FPS on Total-Text, outperforming the previous fastest method by 1.7 points and 70 FPS in terms of accuracy and speed. With TensorRT optimization, the inference speed can be further accelerated to over 600 FPS. Code and models will be released at https://github.com/czczup/FAST.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 51 of its 65 references that are in the map. First posted on arXiv 3 Nov 2021.

Builds on

51 of 65 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2017Mask R-CNNcited by 7,277
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  10. 2019Searching for MobileNetV3cited by 1,994
  11. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  12. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
38 more
  1. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  2. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  3. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  4. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  5. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  6. 2019Character Region Awareness for Text Detectioncited by 278
  7. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 260
  8. 2017EAST: An Efficient and Accurate Scene Text Detectorcited by 248
  9. 2019Real-time Scene Text Detection with Differentiable Binarizationcited by 214
  10. 2017Arbitrary-Oriented Scene Text Detection via Rotation Proposalscited by 176
  11. 2019Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapescited by 171
  12. 2020ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Networkcited by 170
  13. 2017Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognitioncited by 162
  14. 2019Shape Robust Text Detection with Progressive Scale Expansion Networkcited by 147
  15. 2016TextBoxes: A Fast Text Detector with a Single Deep Neural Networkcited by 119
  16. 2018TextBoxes++: A Single-Shot Oriented Scene Text Detectorcited by 119
  17. 2018TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapescited by 114
  18. 2019Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Networkcited by 114
  19. 2018Rotation-Sensitive Regression for Oriented Scene Text Detectioncited by 88
  20. 2016Detecting Text in Natural Image with Connectionist Text Proposal Networkcited by 85
  21. 2017Detecting Curve Text in the Wild: New Dataset and New Solutioncited by 83
  22. 2017Detecting Oriented Text in Natural Images by Linking Segmentscited by 80
  23. 2021Fourier Contour Embedding for Arbitrary-Shaped Text Detectioncited by 80
  24. 2020Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detectioncited by 77
  25. 2020ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detectioncited by 69
  26. 2019Look More Than Once: An Accurate Detector for Text of Arbitrary Shapescited by 66
  27. 2021PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Textcited by 65
  28. 2018PixelLink: Detecting Scene Text via Instance Segmentationcited by 60
  29. 2019NAS-FCOS: Fast Neural Architecture Search for Object Detectioncited by 53
  30. 2018TextField: Learning A Deep Direction Field for Irregular Scene Text Detectioncited by 50
  31. 2021Adaptive Boundary Proposal Network for Arbitrary Shape Text Detectioncited by 47
  32. 2018Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentationcited by 42
  33. 2018Scene Text Detection with Supervised Pyramid Context Networkcited by 34
  34. 2021PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyondcited by 27
  35. 2019Omnidirectional Scene Text Detection with Sequential-free Box Discretizationcited by 26
  36. 2021ViPNAS: Efficient Video Pose Estimation via Neural Architecture Searchcited by 26
  37. 2020ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networkscited by 20
  38. 2020Neural Architecture Design for GPU-Efficient Networkscited by 13

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 1; 2026: 2.

9 papers.

  1. 2023T-MARS: Improving Visual Representations by Circumventing Text Feature Learningcited by 43
  2. 2024CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learningcited by 20
  3. 2024DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthinesscited by 8
  4. 2023MixNet: Toward Accurate Detection of Challenging Scene Text in the Wildcited by 4
  5. 2024Artistic-style text detector and a new Movie-Poster datasetcited by 1
  6. 2024Precision at Scale: Domain-Specific Datasets On-Demandcited by 1
  7. 2025SAViL-Det: Semantic-Aware Vision-Language Model for Multi-Script Text Detectioncited by 0
  8. 2026DocRevive: A Unified Pipeline for Document Text Restorationcited by 0
  9. 2026Comparative Evaluation of Machine Translation Systems on Images with Textcited by 0