MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild

TL;DR

MixNet is a hybrid CNN-Transformer architecture designed to improve the detection of small, challenging scene text in natural images, outperforming existing methods across multiple datasets.

Contribution

Introduces MixNet, combining FSNet and CTBlock modules, with a novel feature shuffling strategy and center line features, achieving state-of-the-art results in scene text detection.

Findings

Significant improvements over existing text detection methods.

Outperforms popular models like PAN, DB, and FAST.

Achieves state-of-the-art results on multiple datasets.

Abstract

Detecting small scene text instances in the wild is particularly challenging, where the influence of irregular positions and nonideal lighting often leads to detection errors. We present MixNet, a hybrid architecture that combines the strengths of CNNs and Transformers, capable of accurately detecting small text from challenging natural scenes, regardless of the orientations, styles, and lighting conditions. MixNet incorporates two key modules: (1) the Feature Shuffle Network (FSNet) to serve as the backbone and (2) the Central Transformer Block (CTBlock) to exploit the 1D manifold constraint of the scene text. We first introduce a novel feature shuffling strategy in FSNet to facilitate the exchange of features across multiple scales, generating high-resolution features superior to popular ResNet and HRNet. The FSNet backbone has achieved significant improvements over many existing text detection methods, including PAN, DB, and FAST. Then we design a complementary CTBlock to leverage center line based features similar to the medial axis of text regions and show that it can outperform contour-based approaches in challenging cases when small scene texts appear closely. Extensive experimental results show that MixNet, which mixes FSNet with CTBlock, achieves state-of-the-art results on multiple scene text detection datasets.