Reducing Domain Gap via Style-Agnostic Networks

10/25/2019
by   Hyeonseob Nam, et al.
0

Deep learning models often fail to maintain their performance on new test domains. This problem has been regarded as a critical limitation of deep learning for real-world applications. One of the main causes of this vulnerability to domain changes is that the model tends to be biased to image styles (i.e. textures). To tackle this problem, we propose Style-Agnostic Networks (SagNets) to encourage the model to focus more on image contents (i.e. shapes) shared across domains but ignore image styles. SagNets consist of three novel techniques: style adversarial learning, style blending and style consistency learning, each of which prevents the model from making decisions based upon style information. In collaboration with a few additional training techniques and an ensemble of several model variants, the proposed method won the 1st place in the semi-supervised domain adaptation task of the Visual Domain Adaptation 2019 (VisDA-2019) Challenge.

READ FULL TEXT
research
03/28/2022

Style-Guided Domain Adaptation for Face Presentation Attack Detection

Domain adaptation (DA) or domain generalization (DG) for face presentati...
research
07/07/2022

Harnessing Out-Of-Distribution Examples via Augmenting Content and Style

Machine learning models are vulnerable to Out-Of-Distribution (OOD) exam...
research
08/16/2019

Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning

Supervised learning algorithms trained on medical images will often fail...
research
02/18/2023

Meta Style Adversarial Training for Cross-Domain Few-Shot Learning

Cross-Domain Few-Shot Learning (CD-FSL) is a recently emerging task that...
research
12/25/2017

Disentangled Representation Learning for Domain Adaptation and Style Transfer

In order to solve unsupervised domain adaptation problem, recent methods...
research
11/08/2022

Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts

Improving model's generalizability against domain shifts is crucial, esp...
research
07/31/2022

Feather-Light Fourier Domain Adaptation in Magnetic Resonance Imaging

Generalizability of deep learning models may be severely affected by the...

Please sign up or login with your details

Forgot password? Click here to reset