# TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers

arXiv: https://arxiv.org/abs/2105.03906 · HTML: https://mlsanity.com/paper/2105.03906/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 72 references that are in the map.
- First posted on arXiv 9 May 2021.

## Builds on (most cited first, 30 of 37)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition](https://mlsanity.com/paper/2103.06495/) (2021)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition](https://mlsanity.com/paper/1811.00751/) (2018)
- [Robust Scene Text Recognition with Automatic Rectification](https://mlsanity.com/paper/1603.03915/) (2016)
- [SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition](https://mlsanity.com/paper/2005.10977/) (2020)
- [Focusing Attention: Towards Accurate Text Recognition in Natural Images](https://mlsanity.com/paper/1709.02054/) (2017)
- [Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes](https://mlsanity.com/paper/1706.10239/) (2017)
- [Sequence-to-Sequence Contrastive Learning for Text Recognition](https://mlsanity.com/paper/2012.10873/) (2020)
- [ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation](https://mlsanity.com/paper/2003.10557/) (2020)
- [SCATTER: Selective Context Attentional Scene Text Recognizer](https://mlsanity.com/paper/2003.11288/) (2020)
- [Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification](https://mlsanity.com/paper/2010.05785/) (2020)
- [OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold](https://mlsanity.com/paper/2006.07491/) (2020)
- [Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition](https://mlsanity.com/paper/1604.08352/) (2016)
- [On Vocabulary Reliance in Scene Text Recognition](https://mlsanity.com/paper/2005.03959/) (2020)

## Built on by (most cited first, 11 of 11)

- [DocVLM: Make Your VLM an Efficient Reader](https://mlsanity.com/paper/2412.08746/) (2024)
- [GRAM: Global Reasoning for Multi-Page VQA](https://mlsanity.com/paper/2401.03411/) (2024)
- [Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach](https://mlsanity.com/paper/2308.08806/) (2023)
- [Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis](https://mlsanity.com/paper/2310.17674/) (2023)
- [Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition](https://mlsanity.com/paper/2307.13244/) (2023)
- [Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation](https://mlsanity.com/paper/2607.21973/) (2026)
- [VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer](https://mlsanity.com/paper/2409.11656/) (2024)
- [Improving Scene Text Recognition for Character-Level Long-Tailed Distribution](https://mlsanity.com/paper/2304.08592/) (2023)
- [Cross-Lingual Learning in Multilingual Scene Text Recognition](https://mlsanity.com/paper/2312.10806/) (2023)
- [Platypus: A Generalized Specialist Model for Reading Text in Various Forms](https://mlsanity.com/paper/2408.14805/) (2024)
- [TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models](https://mlsanity.com/paper/2411.04642/) (2024)

## Abstract (arXiv)

Leveraging the characteristics of convolutional layers, neural networks are extremely effective for pattern recognition tasks. However in some cases, their decisions are based on unintended information leading to high performance on standard benchmarks but also to a lack of generalization to challenging testing conditions and unintuitive failures. Recent work has termed this "shortcut learning" and addressed its presence in multiple domains. In text recognition, we reveal another such shortcut, whereby recognizers overly depend on local image statistics. Motivated by this, we suggest an approach to regulate the reliance on local statistics that improves text recognition performance. Our method, termed TextAdaIN, creates local distortions in the feature map which prevent the network from overfitting to local statistics. It does so by viewing each feature map as a sequence of elements and deliberately mismatching fine-grained feature statistics between elements in a mini-batch. Despite TextAdaIN's simplicity, extensive experiments show its effectiveness compared to other, more complicated methods. TextAdaIN achieves state-of-the-art results on standard handwritten text recognition benchmarks. It generalizes to multiple architectures and to the domain of scene text recognition. Furthermore, we demonstrate that integrating TextAdaIN improves robustness towards more challenging testing conditions. The official Pytorch implementation can be found at https://github.com/amazon-research/textadain-robust-recognition.