Model Architecture

Seeing Out of the Box: End-to-End Pre-Training for Vision-Language Representation Learning CVPR 2021 See Through Gradients: Image Batch Recovery via GradInversion CVPR 2021 Self-Attention Attribution: Interpreting Information Interactions Inside Transformer AAAI 2021 Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-Field Speech Recognition Interspeech 2021 Self-Attention Graph Residual Convolutional Networks for Event Detection with dependency relations EMNLP 2021 Selfish Sparse RNN Training ICML 2021 Self Supervision for Attention Networks WACV 2021 Sentence-Permuted Paragraph Generation EMNLP 2021 Shallow Convolution-Augmented Transformer with Differentiable Neural Computer for Low-Complexity Classification of Variable-Length Acoustic Scene Interspeech 2021 Shape and Material Capture at Home CVPR 2021 SHAPE: Shifted Absolute Position Embedding for Transformers EMNLP 2021 Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped Matrices NeurIPS 2021 Sharpness-aware Minimization for Efficiently Improving Generalization ICLR 2021 Shrinking Bigfoot: Reducing wav2vec 2.0 footprint EMNLP 2021 SIGNET: Efficient Neural Representation for Light Fields ICCV 2021 SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks ICML 2021 Single-dataset Experts for Multi-dataset Question Answering EMNLP 2021 Skim-Attention: Learning to Focus via Document Layout EMNLP 2021 Skip-Convolutions for Efficient Video Processing CVPR 2021 SkipW: Resource Adaptable RNN with Strict Upper Computational Limit ICLR 2021 SparseBERT: Rethinking the Importance Analysis in Self-attention ICML 2021 Sparse Spiking Gradient Descent NeurIPS 2021 Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space NeurIPS 2021 Sparsifying Networks via Subdifferential Inclusion ICML 2021 Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks JMLR 2021