GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition

TL;DR

This paper introduces GA-DAN, a novel network that models cross-domain shifts in both geometry and appearance spaces, improving scene text detection and recognition across different domains.

Contribution

The paper proposes a geometry-aware domain adaptation network with multi-modal spatial learning and disentangled cycle-consistency loss for better cross-domain image translation.

Findings

Improved scene text detection accuracy on cross-domain datasets

Enhanced recognition performance with domain-adapted images

Effective modeling of geometric and appearance shifts in domain adaptation

Abstract

Recent adversarial learning research has achieved very impressive progress for modelling cross-domain data shifts in appearance space but its counterpart in modelling cross-domain shifts in geometry space lags far behind. This paper presents an innovative Geometry-Aware Domain Adaptation Network (GA-DAN) that is capable of modelling cross-domain shifts concurrently in both geometry space and appearance space and realistically converting images across domains with very different characteristics. In the proposed GA-DAN, a novel multi-modal spatial learning technique is designed which converts a source-domain image into multiple images of different spatial views as in the target domain. A new disentangled cycle-consistency loss is introduced which balances the cycle consistency in appearance and geometry spaces and improves the learning of the whole network greatly. The proposed GA-DAN has been evaluated for the classic scene text detection and recognition tasks, and experiments show that the domain-adapted images achieve superior scene text detection and recognition performance while applied to network training.