# Searching a High-Performance Feature Extractor for Text Recognition Network

@article{Zhang2022SearchingAH,
title={Searching a High-Performance Feature Extractor for Text Recognition Network},
author={Hui Zhang and Quanming Yao and James Tin-Yau Kwok and Xiang Bai},
journal={IEEE transactions on pattern analysis and machine intelligence},
year={2022},
volume={PP}
}
• Published 12 September 2022
• Computer Science
• IEEE transactions on pattern analysis and machine intelligence
Feature extractor plays a critical role in text recognition (TR), but customizing its architecture is relatively less explored due to expensive manual tweaking. In this work, inspired by the success of neural architecture search (NAS), we propose to search for suitable feature extractors. We design a domain-specific search space by exploring principles for having good feature extractors. The space includes a 3D-structured space for the spatial model and a transformed-based space for the…
2 Citations

## Figures and Tables from this paper

• Computer Science
ArXiv
• 2022
This work proposes to use neural architecture search (NAS) to design data-speciﬁc message passing architecture for TKG completion and develops a generalized framework to explore topological and temporal information in TKGs.
• Computer Science
Frontiers in Neurorobotics
• 2022
Transformer model is introduced to make Trans-UTPA's policy learning have no action space limitation and can be multi-task parallel, which improves the efficiency and generalization of sample processing.

## References

SHOWING 1-10 OF 89 REFERENCES

• Computer Science
ECCV
• 2020
This work designs a domain-specific search space for STR, which contains both choices on operations and constraints on the downsampling path, and proposes a two-step search algorithm, which decouples operations and downsampled path, for an efficient search in the given space.
• Computer Science
BMVC
• 2018
A novel approach that combines a deep convolutional network with a recurrent Encoder-Decoder network to map an image to a sequence of characters corresponding to the text present in the image, making it both computationally and memory efficient.
• Computer Science
AAAI
• 2020
A decoupled attention network (DAN), which decouples the alignment operation from using historical decoding results, and achieves state-of-the-art performance on multiple text recognition tasks, including offline handwritten text recognition and regular/irregular scene text recognition.
• Computer Science
AAAI
• 2020
TextScanner bears three characteristics: it belongs to the semantic segmentation family, as it generates pixel-wise, multi-channel segmentation maps for character class, position and order, and also adopts RNN for context modeling.
• Computer Science
ECCV
• 2020
Theoretically, the proposed method, dubbed \emph{RobustScanner}, decodes individual characters with dynamic ratio between context and positional clues, and utilizes more positional ones when the decoding sequences with scarce context, and thus is robust and practical.
• Computer Science
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 2019
Extensive text recognition experiments show the SSDAN could efficiently transfer sequence knowledge and validate the promising power of the proposed model towards real world applications in various recognition scenarios, including the natural scene text, handwritten text and even mathematical expression recognition.
• Computer Science
2011 International Conference on Computer Vision
• 2011
While scene text recognition has generally been treated with highly domain-specific methods, the results demonstrate the suitability of applying generic computer vision methods.
• Computer Science
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
• 2018
The arbitrary orientation network (AON) is developed to directly capture the deep features of irregular texts, which are combined into an attention-based decoder to generate character sequence and is comparable to major existing methods in regular datasets.
• Computer Science
AAAI
• 2019
This work proposes an easy-to-implement strong baseline for irregular scene text recognition, using off- the-shelf neural network components and only word-level annotations, and achieves state-of-the-art performance on both regular and irregular sceneText recognition benchmarks.
• Computer Science
ECCV
• 2018
This work designs a multi-task network with an encoder-discriminator-generator architecture to guide the feature of the original image toward that of the clean image, and significantly outperforms the state-of-the-art methods on standard scene text recognition benchmarks in the lexicon-free category.