Unsupervised Domain Expansion for Visual Categorization
arXiv:2104.00233
Abstract
Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has been approached by unsupervised domain adaptation (UDA). Given labeled data from a source domain and unlabeled data from a target domain, UDA seeks for a deep representation that is both discriminative and domain-invariant. While UDA focuses on the target domain, we argue that the performance on both source and target domains matters, as in practice which domain a test example comes from is unknown. In this paper we extend UDA by proposing a new task called unsupervised domain expansion (UDE), which aims to adapt a deep model for the target domain with its unlabeled data, meanwhile maintaining the model's performance on the source domain. We propose Knowledge Distillation Domain Expansion (KDDE) as a general method for the UDE task. Its domain-adaptation module can be instantiated with any existing model. We develop a knowledge distillation based learning mechanism, enabling KDDE to optimize a single objective wherein the source and target domains are equally treated. Extensive experiments on two major benchmarks, i.e., Office-Home and DomainNet, show that KDDE compares favorably against four competitive baselines, i.e., DDC, DANN, DAAN, and CDAN, for both UDA and UDE tasks. Our study also reveals that the current UDA models improve their performance on the target domain at the cost of noticeable performance loss on the source domain.
arXiv commentaccepted as regular paper by ACM Transactions on Multimedia Computing Communications and Applications (TOMM). Project URL https://github.com/li-xirong/ude
References in corpus (9)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Distilling the Knowledge in a Neural Network
- Deep Domain Confusion: Maximizing for Domain Invariance
- Conditional Adversarial Domain Adaptation
- Adversarial Discriminative Domain Adaptation
- Contrastive Adaptation Network for Unsupervised Domain Adaptation
- Adversarial Teacher-Student Learning for Unsupervised Domain Adaptation
- Semi-supervised Domain Adaptation via Minimax Entropy
- Confidence Regularized Self-Training