Contrastive Adaptation Network for Unsupervised Domain Adaptation

Abstract

Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain. Previous methods minimize the domain discrepancy neglecting the class information, which may lead to misalignment and poor generalization performance. To address this issue, this paper proposes Contrastive Adaptation Network (CAN) optimizing a new metric which explicitly models the intra-class domain discrepancy and the inter-class domain discrepancy. We design an alternating update strategy for training CAN in an end-to-end manner. Experiments on two real-world benchmarks Office-31 and VisDA-2017 demonstrate that CAN performs favorably against the state-of-the-art methods and produces more discriminative features.

Accepted by CVPR 2019

References in corpus (7)

• In Defense of the Triplet Loss for Person Re-Identification
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unsupervised Domain Adaptation with Residual Transfer Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• Domain Separation Networks
• VisDA: The Visual Domain Adaptation Challenge

Cited by in corpus (16)

• A Survey of Deep Learning-based Object Detection
• DeepMerge II: Building Robust Deep Learning Algorithms for Merging Galaxy Identification Across Domains
• Cycle-Contrast for Self-Supervised Video Representation Learning
• Harmonizing Transferability and Discriminability for Adapting Object Detectors
• Combining Self-Supervised and Supervised Learning with Noisy Labels
• Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
• Unsupervised Domain Adaptation by Uncertain Feature Alignment
• Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019
• Dynamic Feature Alignment for Semi-supervised Domain Adaptation
• Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
• Box-Adapt: Domain-Adaptive Medical Image Segmentation using Bounding BoxSupervision
• Multi-Purposing Domain Adaptation Discriminators for Pseudo Labeling Confidence
• Unsupervised Domain Expansion for Visual Categorization
• Bi-Directional Generation for Unsupervised Domain Adaptation
• T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation
• KL Guided Domain Adaptation