Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition
This addresses the need for lightweight text recognition models in applications with large vocabularies, though it is an incremental improvement over existing transformer-based methods.
The paper tackles the problem of rapidly expanding model size in scene text recognition, especially for large lexicons like Chinese, by proposing Hamming OCR, which uses a Hamming classifier with locality sensitive hashing to make parameters independent of vocabulary size, achieving competitive results on multiple datasets including one with over 20,000 characters.
Recently, inspired by Transformer, self-attention-based scene text recognition approaches have achieved outstanding performance. However, we find that the size of model expands rapidly with the lexicon increasing. Specifically, the number of parameters for softmax classification layer and output embedding layer are proportional to the vocabulary size. It hinders the development of a lightweight text recognition model especially applied for Chinese and multiple languages. Thus, we propose a lightweight scene text recognition model named Hamming OCR. In this model, a novel Hamming classifier, which adopts locality sensitive hashing (LSH) algorithm to encode each character, is proposed to replace the softmax regression and the generated LSH code is directly employed to replace the output embedding. We also present a simplified transformer decoder to reduce the number of parameters by removing the feed-forward network and using cross-layer parameter sharing technique. Compared with traditional methods, the number of parameters in both classification and embedding layers is independent on the size of vocabulary, which significantly reduces the storage requirement without loss of accuracy. Experimental results on several datasets, including four public benchmaks and a Chinese text dataset synthesized by SynthText with more than 20,000 characters, shows that Hamming OCR achieves competitive results.