Model Architecture

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective ICLR 2021 Neural Architecture Search without Training ICML 2021 Neural Attention-Aware Hierarchical Topic Model EMNLP 2021 Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers AISTATS 2021 Neural Image Compression via Attentional Multi-Scale Back Projection and Frequency Decomposition ICCV 2021 Neural Pruning via Growing Regularization ICLR 2021 Neural Sentence Ordering Based on Constraint Graphs AAAI 2021 Neural Speaker Extraction with Speaker-Speech Cross-Attention Network Interspeech 2021 Nondeterminism and Instability in Neural Network Optimization ICML 2021 NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-end Learning and Control ICLR 2021 Nyströmformer: A Nyström-based Algorithm for Approximating Self-Attention AAAI 2021 Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-ID ICCV 2021 On Geodesic Distances and Contextual Embedding Compression for Text Classification NAACL 2021 ONION: A Simple and Effective Defense Against Textual Backdoor Attacks EMNLP 2021 Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers Interspeech 2021 Online-Trained Upsampler for Deep Low Complexity Video Compression ICCV 2021 Only Train Once: A One-Shot Neural Network Training And Pruning Framework NeurIPS 2021 On Robustness of Neural Semantic Parsers EACL 2021 On the Generalization Properties of Adversarial Training AISTATS 2021 On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent ICML 2021 On the number of linear functions composing deep neural network: Towards a refined definition of neural networks complexity AISTATS 2021 On the Predictability of Pruning Across Scales ICML 2021 OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization AAAI 2021 Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks ICLR 2021 Optimally Encoding Inductive Biases into the Transformer Improves End-to-End Speech Translation Interspeech 2021