Aggregated Text Transformer for Scene Text Detection
This addresses the problem of detecting text in complex scenes for computer vision applications, but it appears incremental as it builds on existing Transformer and multi-scale strategies.
The paper tackles scene text detection in natural images by proposing the Aggregated Text Transformer (ATTR), which uses a multi-scale self-attention mechanism to represent texts, resulting in effective detection as demonstrated on public datasets.
This paper explores the multi-scale aggregation strategy for scene text detection in natural images. We present the Aggregated Text TRansformer(ATTR), which is designed to represent texts in scene images with a multi-scale self-attention mechanism. Starting from the image pyramid with multiple resolutions, the features are first extracted at different scales with shared weight and then fed into an encoder-decoder architecture of Transformer. The multi-scale image representations are robust and contain rich information on text contents of various sizes. The text Transformer aggregates these features to learn the interaction across different scales and improve text representation. The proposed method detects scene texts by representing each text instance as an individual binary mask, which is tolerant of curve texts and regions with dense instances. Extensive experiments on public scene text detection datasets demonstrate the effectiveness of the proposed framework.