Model Architecture

Tractable structured natural-gradient descent using local parameterizations ICML 2021 Training Graph Neural Networks with 1000 Layers ICML 2021 Training independent subnetworks for robust prediction ICLR 2021 Training Neural Networks with Fixed Sparse Masks NeurIPS 2021 Training with Quantization Noise for Extreme Model Compression ICLR 2021 Transformer in Transformer NeurIPS 2021 Tripartite Information Mining and Integration for Image Matting ICCV 2021 Triple M: A Practical Text-to-Speech Synthesis System with Multi-Guidance Attention and Multi-Band Multi-Time LPCNet Interspeech 2021 Truly Shift-Invariant Convolutional Neural Networks CVPR 2021 TUDa at WMT21: Sentence-Level Direct Assessment with Adapters EMNLP 2021 Tuning IR-Cut Filter for Illumination-Aware Spectral Reconstruction From RGB CVPR 2021 Tutorial: End-to-End Speech Translation EACL 2021 Uncertainty-aware Binary Neural Networks IJCAI 2021 Understanding and Mitigating Exploding Inverses in Invertible Neural Networks AISTATS 2021 Understanding and Overcoming the Challenges of Efficient Transformer Quantization EMNLP 2021 Unfolding Taylor's Approximations for Image Restoration NeurIPS 2021 Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution ICCV 2021 Using latent space regression to analyze and leverage compositionality in GANs ICLR 2021 VaPiD: A Rapid Vanishing Point Detector via Learned Optimizers ICCV 2021 Variational Information Bottleneck for Effective Low-Resource Audio Classification Interspeech 2021 Vector Neurons: A General Framework for SO(3)-Equivariant Networks ICCV 2021 VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment EMNLP 2021 Video Action Recognition with Neural Architecture Search ACML 2021 Video-Based Person Re-Identification With Spatial and Temporal Memory Networks ICCV 2021 ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision ICML 2021