Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation
arXiv:2002.03642
Abstract
In this paper, we introduce a collaborative training algorithm of balanced random forests with convolutional neural networks for domain adaptation tasks. In real scenarios, most domain adaptation algorithms face the challenges from noisy, insufficient training data and open set categorization. In such cases, conventional methods suffer from overfitting and fail to successfully transfer the knowledge of the source to the target domain. To address these issues, the following two techniques are proposed. First, we introduce the optimized decision tree construction method with convolutional neural networks, in which the data at each node are split into equal sizes while maximizing the information gain. It generates balanced decision trees on deep features because of the even-split constraint, which contributes to enhanced discrimination power and reduced overfitting problem. Second, to tackle the domain misalignment problem, we propose the domain alignment loss which penalizes uneven splits of the source and target domain data. By collaboratively optimizing the information gain of the labeled source data as well as the entropy of unlabeled target data distributions, the proposed CoBRF algorithm achieves significantly better performance than the state-of-the-art methods.
References in corpus (10)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Learning Transferable Features with Deep Adaptation Networks
- Deep Domain Confusion: Maximizing for Domain Invariance
- Conditional Adversarial Domain Adaptation
- Unsupervised Domain Adaptation with Residual Transfer Networks
- Algorithms and Theory for Multiple-Source Adaptation
- To tune or not to tune the number of trees in random forest?
- Domain-Symmetric Networks for Adversarial Domain Adaptation
- SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person
- Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration