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

07/23/2019
by   Fangneng Zhan, et al.
14

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.

READ FULL TEXT

page 1

page 3

page 7

page 8

research
11/15/2019

Curriculum Self-Paced Learning for Cross-Domain Object Detection

Training (source) domain bias affects state-of-the-art object detectors,...
research
09/19/2020

Adversarial Consistent Learning on Partial Domain Adaptation of PlantCLEF 2020 Challenge

Domain adaptation is one of the most crucial techniques to mitigate the ...
research
11/26/2019

Spatial-Aware GAN for Unsupervised Person Re-identification

The recent person re-identification research has achieved great success ...
research
03/24/2021

DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation

In this paper, we present DRANet, a network architecture that disentangl...
research
01/26/2019

Scene Text Synthesis for Efficient and Effective Deep Network Training

A large amount of annotated training images is critical for training acc...
research
05/02/2017

Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner

Impressive image captioning results are achieved in domains with plenty ...
research
07/29/2021

Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation

Deep neural networks have significantly improved appearance-based gaze e...

Please sign up or login with your details

Forgot password? Click here to reset