Neural Networks

Functional Neural Networks for Parametric Image Restoration Problems NeurIPS 2021 Functional Regularization for Reinforcement Learning via Learned Fourier Features NeurIPS 2021 Funnel Deep Complex U-Net for Phase-Aware Speech Enhancement Interspeech 2021 Fusion-Net: Time-Frequency Information Fusion Y-Network for Speech Enhancement Interspeech 2021 Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition Interspeech 2021 FVC: A New Framework Towards Deep Video Compression in Feature Space CVPR 2021 GAN-Control: Explicitly Controllable GANs ICCV 2021 Gaussian Context Transformer CVPR 2021 Gaussian Kernel Mixture Network for Single Image Defocus Deblurring NeurIPS 2021 Gaussian Process Priors for View-Aware Inference AAAI 2021 Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network CoNLL 2021 Generalization Guarantees for Neural Architecture Search with Train-Validation Split ICML 2021 General Nonlinearities in SO(2)-Equivariant CNNs NeurIPS 2021 Generating Attribution Maps With Disentangled Masked Backpropagation ICCV 2021 Generating Deep Networks Explanations with Robust Attribution Alignment ACML 2021 Generating High-Quality Explanations for Navigation in Partially-Revealed Environments NeurIPS 2021 Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances ICML 2021 Geometry Uncertainty Projection Network for Monocular 3D Object Detection ICCV 2021 GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles NeurIPS 2021 GIRAFFE: Representing Scenes As Compositional Generative Neural Feature Fields CVPR 2021 Global Convergence of Three-layer Neural Networks in the Mean Field Regime ICLR 2021 Global Filter Networks for Image Classification NeurIPS 2021 Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes ICML 2021 Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs ICML 2021 Going Deeper With Directly-Trained Larger Spiking Neural Networks AAAI 2021