Self-supervised Domain Adaptation for Computer Vision Tasks

Abstract

Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In this work, we propose a generic method for self-supervised domain adaptation, using object recognition and semantic segmentation of urban scenes as use cases. Focusing on simple pretext/auxiliary tasks (e.g. image rotation prediction), we assess different learning strategies to improve domain adaptation effectiveness by self-supervision. Additionally, we propose two complementary strategies to further boost the domain adaptation accuracy on semantic segmentation within our method, consisting of prediction layer alignment and batch normalization calibration. The experimental results show adaptation levels comparable to most studied domain adaptation methods, thus, bringing self-supervision as a new alternative for reaching domain adaptation. The code is available at https://github.com/Jiaolong/self-supervised-da.

arXiv commentAccepted by IEEE Access

References in corpus (14)

• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• Learning Transferable Features with Deep Adaptation Networks
• Deep Visual Domain Adaptation: A Survey
• Unsupervised Representation Learning by Predicting Image Rotations
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Revisiting Batch Normalization For Practical Domain Adaptation
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Improvements to context based self-supervised learning
• Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
• A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes

Cited by in corpus (24)

• Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
• Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
• Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels
• Self-Supervised Learning for Domain Adaptation on Point-Clouds
• M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training
• Multimodal Across Domains Gaze Target Detection
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
• Open-Set Hypothesis Transfer with Semantic Consistency
• A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds
• Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
• Co-training for On-board Deep Object Detection
• One-Shot Unsupervised Cross-Domain Detection
• Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
• Action-Based Representation Learning for Autonomous Driving
• Self-Supervised Euphemism Detection and Identification for Content Moderation
• Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation
• Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources
• Self-Supervised Domain Adaptation with Consistency Training
• RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
• Exploring Data Aggregation and Transformations to Generalize across Visual Domains
• Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation
• Domain Agnostic Learning for Unbiased Authentication