mlsanityData to 14 Oct 2026

FEDS -- Filtered Edit Distance Surrogate

arXiv 2103.04635 ↗First posted 8 Mar 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper proposes a procedure to train a scene text recognition model using a robust learned surrogate of edit distance. The proposed method borrows from self-paced learning and filters out the training examples that are hard for the surrogate. The filtering is performed by judging the quality of the approximation, using a ramp function, enabling end-to-end training. Following the literature, the experiments are conducted in a post-tuning setup, where a trained scene text recognition model is tuned using the learned surrogate of edit distance. The efficacy is demonstrated by improvements on various challenging scene text datasets such as IIIT-5K, SVT, ICDAR, SVTP, and CUTE. The proposed method provides an average improvement of 11.2 % on total edit distance and an error reduction of 9.5% on accuracy.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 30 of its 55 references that are in the map. First posted on arXiv 8 Mar 2021.

Builds on

30 of 55 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  4. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  5. 2017Improved Training of Wasserstein GANscited by 2,235
  6. 2015Spatial Transformer Networkscited by 1,429
  7. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 520
  8. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  9. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
  10. 2019What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysiscited by 191
  11. 2019Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapescited by 171
  12. 2019ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019cited by 139
18 more
  1. 2020Towards Accurate Scene Text Recognition with Semantic Reasoning Networkscited by 131
  2. 2018Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognitioncited by 130
  3. 2014Reading Text in the Wild with Convolutional Neural Networkscited by 122
  4. 2016Robust Scene Text Recognition with Automatic Rectificationcited by 121
  5. 2020SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognitioncited by 119
  6. 2018Scene Text Detection and Recognition: The Deep Learning Eracited by 114
  7. 2019Decoupled Attention Network for Text Recognitioncited by 102
  8. 2020RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognitioncited by 85
  9. 2018ESIR: End-to-end Scene Text Recognition via Iterative Image Rectificationcited by 79
  10. 2020SCATTER: Selective Context Attentional Scene Text Recognizercited by 69
  11. 2018Scene Text Recognition from Two-Dimensional Perspectivecited by 57
  12. 2015Reading Scene Text in Deep Convolutional Sequencescited by 44
  13. 2020UnrealText: Synthesizing Realistic Scene Text Images from the Unreal Worldcited by 43
  14. 2015Loss Functions for Top-k Error: Analysis and Insightscited by 38
  15. 2018E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Textcited by 21
  16. 2020Learning Surrogates via Deep Embeddingcited by 11
  17. 2019Selective Style Transfer for Textcited by 8
  18. 2020Text Recognition -- Real World Data and Where to Find Themcited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 0; 2024: 1; 2025: 2.

5 papers.

  1. 2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
  2. 2022Generalized Differentiable RANSACcited by 30
  3. 2025Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCRcited by 1
  4. 2024Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognitioncited by 0
  5. 2025Towards Scalable Lottery Ticket Networks using Genetic Algorithmscited by 0