Transferrable Prototypical Networks for Unsupervised Domain Adaptation

Abstract

In this paper, we introduce a new idea for unsupervised domain adaptation via a remold of Prototypical Networks, which learn an embedding space and perform classification via a remold of the distances to the prototype of each class. Specifically, we present Transferrable Prototypical Networks (TPN) for adaptation such that the prototypes for each class in source and target domains are close in the embedding space and the score distributions predicted by prototypes separately on source and target data are similar. Technically, TPN initially matches each target example to the nearest prototype in the source domain and assigns an example a "pseudo" label. The prototype of each class could then be computed on source-only, target-only and source-target data, respectively. The optimization of TPN is end-to-end trained by jointly minimizing the distance across the prototypes on three types of data and KL-divergence of score distributions output by each pair of the prototypes. Extensive experiments are conducted on the transfers across MNIST, USPS and SVHN datasets, and superior results are reported when comparing to state-of-the-art approaches. More remarkably, we obtain an accuracy of 80.4% of single model on VisDA 2017 dataset.

CVPR 2019 Oral

References in corpus (10)

• Prototypical Networks for Few-shot Learning
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Unsupervised Domain Adaptation with Residual Transfer Networks
• VisDA: The Visual Domain Adaptation Challenge
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Adversarial Discriminative Domain Adaptation
• Fully Convolutional Adaptation Networks for Semantic Segmentation
• YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video

Cited by in corpus (17)

• Hyperspherical Prototype Networks
• Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
• Harmonizing Transferability and Discriminability for Adapting Object Detectors
• Prototypical Partial Optimal Transport for Universal Domain Adaptation
• Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
• Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
• Adversarial Bi-Regressor Network for Domain Adaptive Regression
• Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019
• Hyperbolic Busemann Learning with Ideal Prototypes
• Joint Semantic Domain Alignment and Target Classifier Learning for Unsupervised Domain Adaptation
• Learning a Unified Sample Weighting Network for Object Detection
• Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains
• Transferring and Regularizing Prediction for Semantic Segmentation
• Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation
• Self-Adaptive Partial Domain Adaptation
• Bi-Directional Generation for Unsupervised Domain Adaptation
• T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation