DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting

TL;DR

DEER introduces a detection-agnostic end-to-end scene text recognizer that relies on reference points rather than precise detection, improving robustness to detection errors and simplifying the text spotting process.

Contribution

It proposes a novel detection-agnostic framework that reduces dependency on detection accuracy by using reference points, enabling effective recognition without detailed region annotations.

Findings

Achieves competitive results on standard benchmarks.

Demonstrates robustness to detection errors.

Eliminates need for arbitrarily-shaped detectors.

Abstract

Recent end-to-end scene text spotters have achieved great improvement in recognizing arbitrary-shaped text instances. Common approaches for text spotting use region of interest pooling or segmentation masks to restrict features to single text instances. However, this makes it hard for the recognizer to decode correct sequences when the detection is not accurate i.e. one or more characters are cropped out. Considering that it is hard to accurately decide word boundaries with only the detector, we propose a novel Detection-agnostic End-to-End Recognizer, DEER, framework. The proposed method reduces the tight dependency between detection and recognition modules by bridging them with a single reference point for each text instance, instead of using detected regions. The proposed method allows the decoder to recognize the texts that are indicated by the reference point, with features from the whole image. Since only a single point is required to recognize the text, the proposed method enables text spotting without an arbitrarily-shaped detector or bounding polygon annotations. Experimental results present that the proposed method achieves competitive results on regular and arbitrarily-shaped text spotting benchmarks. Further analysis shows that DEER is robust to the detection errors. The code and dataset will be publicly available.