# AutoSTR: Efficient Backbone Search for Scene Text Recognition

arXiv: https://arxiv.org/abs/2003.06567 · HTML: https://mlsanity.com/paper/2003.06567/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2020.

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

- [Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition](https://mlsanity.com/paper/2207.00193/) (2022)
- [Primitive Representation Learning for Scene Text Recognition](https://mlsanity.com/paper/2105.04286/) (2021)
- [Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution](https://mlsanity.com/paper/2112.08171/) (2021)
- [FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation](https://mlsanity.com/paper/2111.02394/) (2021)
- [Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition](https://mlsanity.com/paper/2105.06229/) (2021)
- [Searching a High-Performance Feature Extractor for Text Recognition Network](https://mlsanity.com/paper/2209.13139/) (2022)
- [TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance](https://mlsanity.com/paper/2111.08314/) (2021)
- [IterVM: Iterative Vision Modeling Module for Scene Text Recognition](https://mlsanity.com/paper/2204.02630/) (2022)
- [Portmanteauing Features for Scene Text Recognition](https://mlsanity.com/paper/2211.05036/) (2022)
- [Scene Text Recognition with Image-Text Matching-guided Dictionary](https://mlsanity.com/paper/2305.04524/) (2023)
- [Disentanglement and Compositionality of Letter Identity and Letter Position in Variational Auto-Encoder Vision Models](https://mlsanity.com/paper/2412.10446/) (2024)

## Abstract (arXiv)

Scene text recognition (STR) is very challenging due to the diversity of text instances and the complexity of scenes. The community has paid increasing attention to boost the performance by improving the pre-processing image module, like rectification and deblurring, or the sequence translator. However, another critical module, i.e., the feature sequence extractor, has not been extensively explored. In this work, inspired by the success of neural architecture search (NAS), which can identify better architectures than human-designed ones, we propose automated STR (AutoSTR) to search data-dependent backbones to boost text recognition performance. First, we design a domain-specific search space for STR, which contains both choices on operations and constraints on the downsampling path. Then, we propose a two-step search algorithm, which decouples operations and downsampling path, for an efficient search in the given space. Experiments demonstrate that, by searching data-dependent backbones, AutoSTR can outperform the state-of-the-art approaches on standard benchmarks with much fewer FLOPS and model parameters.