Neural Networks Regularization Through Class-wise Invariant Representation Learning
Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification task when few training samples are available. We attempt to solve this issue by proposing a new regularization term that constrains the hidden layers of a network to learn class-wise invariant representations. In our regularization framework, learning invariant representations is generalized to the class membership where samples with the same class should have the same representation. Numerical experiments over MNIST and its variants showed that our proposal helps improving the generalization of neural network particularly when trained with few samples. We provide the source code of our framework https://github.com/sbelharbi/learning-class-invariant-features .
Code (1)
Tasks
General ClassificationRepresentation LearningSimilar Papers 제목 키워드 기반
Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose
Domain gap between synthetic and real data in visual regression (e.g. 6D pose estimation) is bridged in this paper via global feature alignment and local refinement on the coarse classification of discretized anchor clas…
6D Pose EstimationDomain AdaptationPose Estimationregression+2CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions
While deep learning based approaches have demonstrated expert-level performance in dermatological diagnosis tasks, they have also been shown to exhibit biases toward certain demographic attributes, particularly skin type…
16kFairnessLesion ClassificationRepresentation Learning+1Robustness through Data Augmentation Loss Consistency
While deep learning through empirical risk minimization (ERM) has succeeded at achieving human-level performance at a variety of complex tasks, ERM is not robust to distribution shifts or adversarial attacks. Synthetic d…
Multi-domain Dialogue State TrackingVisual Question AnsweringVisual Question Answering (VQA)Learning an MR acquisition-invariant representation using Siamese neural networks
Generalization of voxelwise classifiers is hampered by differences between MRI-scanners, e.g. different acquisition protocols and field strengths. To address this limitation, we propose a Siamese neural network (MRAI-NET…
Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation
Data augmentation has been proven to be an effective technique for developing machine learning models that are robust to known classes of distributional shifts (e.g., rotations of images), and alignment regularization is…
Data Augmentation