Learning from a Complementary-label Source Domain: Theory and Algorithms
arXiv:2008.01454
Abstract
In unsupervised domain adaptation (UDA), a classifier for the target domain is trained with massive true-label data from the source domain and unlabeled data from the target domain. However, collecting fully-true-label data in the source domain is high-cost and sometimes impossible. Compared to the true labels, a complementary label specifies a class that a pattern does not belong to, hence collecting complementary labels would be less laborious than collecting true labels. Thus, in this paper, we propose a novel setting that the source domain is composed of complementary-label data, and a theoretical bound for it is first proved. We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA). To this end, a complementary label adversarial network} (CLARINET) is proposed to solve CC-UDA and PC-UDA problems. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines on handwritten-digits-recognition and objects-recognition tasks.
arXiv commentarXiv admin note: text overlap with arXiv:2007.14612
References in corpus (18)
- Conditional Generative Adversarial Nets
- Natural Language Processing (almost) from Scratch
- How transferable are features in deep neural networks?
- Learning Transferable Features with Deep Adaptation Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Conditional Adversarial Domain Adaptation
- Asymmetric Tri-training for Unsupervised Domain Adaptation
- A DIRT-T Approach to Unsupervised Domain Adaptation
- Bridging Theory and Algorithm for Domain Adaptation
- Generalization and Equilibrium in Generative Adversarial Nets (GANs)
- LSDA: Large Scale Detection Through Adaptation
- Masking: A New Perspective of Noisy Supervision
- Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
- Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain
- Learning from Complementary Labels
- Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning
- Learning Deep Kernels for Non-Parametric Two-Sample Tests
- Open Set Domain Adaptation: Theoretical Bound and Algorithm