STELA: A Real-Time Scene Text Detector with Learned Anchor

TL;DR

STELA introduces a real-time, single-reference-box scene text detection method that leverages learned anchors, achieving high accuracy and efficiency, and simplifying anchor design compared to traditional multi-anchor approaches.

Contribution

The paper proposes a novel one-stage scene text detector using learned anchors with a single reference box per location, inspired by two-stage R-CNN frameworks.

Findings

Achieves 26.5 fps at 800p resolution.

Surpasses all existing anchor-based scene text detectors.

Demonstrates competitive performance on public benchmarks.

Abstract

To achieve high coverage of target boxes, a normal strategy of conventional one-stage anchor-based detectors is to utilize multiple priors at each spatial position, especially in scene text detection tasks. In this work, we present a simple and intuitive method for multi-oriented text detection where each location of feature maps only associates with one reference box. The idea is inspired from the twostage R-CNN framework that can estimate the location of objects with any shape by using learned proposals. The aim of our method is to integrate this mechanism into a onestage detector and employ the learned anchor which is obtained through a regression operation to replace the original one into the final predictions. Based on RetinaNet, our method achieves competitive performances on several public benchmarks with a totally real-time efficiency (26:5fps at 800p), which surpasses all of anchor-based scene text detectors. In addition, with less attention on anchor design, we believe our method is easy to be applied on other analogous detection tasks. The code will publicly available at https://github.com/xhzdeng/stela.