Self-Challenging Improves Cross-Domain Generalization
This addresses the challenge of poor performance when CNNs are tested on data from different distributions, which is a critical issue for real-world applications like autonomous driving or medical imaging, though it appears incremental as it builds on existing CNN training methods.
The paper tackles the problem of cross-domain image classification by introducing Representation Self-Challenging (RSC), a training heuristic that discards dominant features to force networks to activate remaining label-correlated features, resulting in significant improvements in generalization to out-of-domain data without extra parameters.
Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels. When the training and testing data are under similar distributions, their dominant features are similar, which usually facilitates decent performance on the testing data. The performance is nonetheless unmet when tested on samples from different distributions, leading to the challenges in cross-domain image classification. We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data. RSC iteratively challenges (discards) the dominant features activated on the training data, and forces the network to activate remaining features that correlates with labels. This process appears to activate feature representations applicable to out-of-domain data without prior knowledge of new domain and without learning extra network parameters. We present theoretical properties and conditions of RSC for improving cross-domain generalization. The experiments endorse the simple, effective and architecture-agnostic nature of our RSC method.