Regularization

Regularization on Spatio-Temporally Smoothed Feature for Action Recognition CVPR 2020 Regularizing CNN Transfer Learning With Randomised Regression CVPR 2020 Regularizing Neural Networks via Minimizing Hyperspherical Energy CVPR 2020 STEER : Simple Temporal Regularization For Neural ODE NeurIPS 2020 A Logic-Driven Framework for Consistency of Neural Models EMNLP 2019 Guided Dropout AAAI 2019 Learning Not to Learn: Training Deep Neural Networks With Biased Data CVPR 2019 Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization ACL 2019 MixUp as Locally Linear Out-of-Manifold Regularization AAAI 2019 P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification CVPR 2019 Regularizing Neural Networks via Stochastic Branch Layers ACML 2019 Representation Degeneration Problem in Training Natural Language Generation Models ICLR 2019 Robustness via Curvature Regularization, and Vice Versa CVPR 2019 Tangent-Normal Adversarial Regularization for Semi-Supervised Learning CVPR 2019 Weighted Channel Dropout for Regularization of Deep Convolutional Neural Network AAAI 2019 Can We Gain More from Orthogonality Regularizations in Training Deep Networks? NeurIPS 2018 Collaboratively Weighting Deep and Classic Representation via l_2 Regularization for Image Classification ACML 2018 Improving Neural Language Models with Weight Norm Initialization and Regularization EMNLP 2018 LDMNet: Low Dimensional Manifold Regularized Neural Networks CVPR 2018 Learning towards Minimum Hyperspherical Energy NeurIPS 2018 Regularization Learning Networks: Deep Learning for Tabular Datasets NeurIPS 2018 Removing the Feature Correlation Effect of Multiplicative Noise NeurIPS 2018 Supervised autoencoders: Improving generalization performance with unsupervised regularizers NeurIPS 2018 All You Need Is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks With Orthonormality and Modulation CVPR 2017 Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation CVPR 2017