Neuron Coverage-Guided Domain Generalization
arXiv:2103.00229
Abstract
This paper focuses on the domain generalization task where domain knowledge is unavailable, and even worse, only samples from a single domain can be utilized during training. Our motivation originates from the recent progresses in deep neural network (DNN) testing, which has shown that maximizing neuron coverage of DNN can help to explore possible defects of DNN (i.e., misclassification). More specifically, by treating the DNN as a program and each neuron as a functional point of the code, during the network training we aim to improve the generalization capability by maximizing the neuron coverage of DNN with the gradient similarity regularization between the original and augmented samples. As such, the decision behavior of the DNN is optimized, avoiding the arbitrary neurons that are deleterious for the unseen samples, and leading to the trained DNN that can be better generalized to out-of-distribution samples. Extensive studies on various domain generalization tasks based on both single and multiple domain(s) setting demonstrate the effectiveness of our proposed approach compared with state-of-the-art baseline methods. We also analyze our method by conducting visualization based on network dissection. The results further provide useful evidence on the rationality and effectiveness of our approach.
arXiv commentACCEPTED TO TPAMI
References in corpus (13)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- DeepXplore: Automated Whitebox Testing of Deep Learning Systems
- Understanding deep learning requires rethinking generalization
- Domain Generalization via Invariant Feature Representation
- Domain Generalization via Model-Agnostic Learning of Semantic Features
- Understanding the Role of Individual Units in a Deep Neural Network
- Wasserstein Auto-Encoders
- Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
- Learning to Generalize: Meta-Learning for Domain Generalization
- Learning Robust Representations by Projecting Superficial Statistics Out
- Episodic Training for Domain Generalization
- Learning to Generate Novel Domains for Domain Generalization