DLOW: Domain Flow for Adaptation and Generalization

2018/12/13 by Rui Gong, Gong, Rui, Wen Li +5 · 8 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1812.05418

Abstract

In this work, we present a domain flow generation(DLOW) model to bridge two different domains by generating a continuous sequence of intermediate domains flowing from one domain to the other. The benefits of our DLOW model are two-fold. First, it is able to transfer source images into different styles in the intermediate domains. The transferred images smoothly bridge the gap between source and target domains, thus easing the domain adaptation task. Second, when multiple target domains are provided for training, our DLOW model is also able to generate new styles of images that are unseen in the training data. We implement our DLOW model based on CycleGAN. A domainness variable is introduced to guide the model to generate the desired intermediate domain images. In the inference phase, a flow of various styles of images can be obtained by varying the domainness variable. We demonstrate the effectiveness of our model for both cross-domain semantic segmentation and the style generalization tasks on benchmark datasets. Our implementation is available at https://github.com/ETHRuiGong/DLOW.

Cited by

• Federated Domain Generalization with Latent Space Inversion
• RobustSurg: Tackling domain generalisation for out-of-distribution surgical scene segmentation
• Domain Generalization for Semantic Segmentation: A Survey
• DPGLA: Bridging the Gap between Synthetic and Real Data for Unsupervised Domain Adaptation in 3D LiDAR Semantic Segmentation
• ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation
• Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations
• Class Unbiasing for Generalization in Medical Diagnosis
• Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models

Related

• Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation
• Unsupervised Domain Adaptation using Generative Models and Self-ensembling
• WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation
• CycleMix: Mixing Source Domains for Domain Generalization in Style-Dependent Data
• Unsupervised Domain Adaptation by Optical Flow Augmentation in Semantic Segmentation