Searching a High-Performance Feature Extractor for Text Recognition Network

TL;DR

This paper introduces a neural architecture search method to automatically discover high-performance feature extractors for text recognition, outperforming existing methods in accuracy and latency.

Contribution

It designs a domain-specific search space and a two-stage search algorithm tailored for text recognition feature extractors, addressing the limitations of existing NAS methods.

Findings

Achieves better recognition accuracy than state-of-the-art methods.

Reduces latency while maintaining high performance.

Provides insights through extensive ablation studies.

Abstract

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 sequential model. As the space is huge and complexly structured, no existing NAS algorithms can be applied. We propose a two-stage algorithm to effectively search in the space. In the first stage, we cut the space into several blocks and progressively train each block with the help of an auxiliary head. We introduce the latency constraint into the second stage and search sub-network from the trained supernet via natural gradient descent. In experiments, a series of ablation studies are performed to better understand the designed space, search algorithm, and searched architectures. We also compare the proposed method with various state-of-the-art ones on both hand-written and scene TR tasks. Extensive results show that our approach can achieve better recognition performance with less latency.