DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting
This addresses text spotting for computer vision applications by reducing dependency between detection and recognition, though it appears incremental as it builds on existing end-to-end approaches.
The paper tackles the problem of inaccurate text detection causing recognition errors in scene text spotting by proposing DEER, a detection-agnostic framework that uses a single reference point per text instance instead of detected regions, achieving competitive results on benchmarks and showing robustness to detection errors.
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.