Model Architecture

Revisiting Model Stitching to Compare Neural Representations NeurIPS 2021 Revisiting Weight Initialization of Deep Neural Networks ACML 2021 ReZero is all you need: fast convergence at large depth UAI 2021 RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks CoRL 2021 Riggable 3D Face Reconstruction via In-Network Optimization CVPR 2021 R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating ICCV 2021 RMSMP: A Novel Deep Neural Network Quantization Framework With Row-Wise Mixed Schemes and Multiple Precisions ICCV 2021 Robust Pruning at Initialization ICLR 2021 Rotate to Attend: Convolutional Triplet Attention Module WACV 2021 Rotation-Invariant Gait Identification with Quaternion Convolutional Neural Networks (Student Abstract) AAAI 2021 RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection CVPR 2021 RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices AAAI 2021 Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks EMNLP 2021 S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks NeurIPS 2021 SA-BNN: State-Aware Binary Neural Network AAAI 2021 Saliency Prediction With External Knowledge WACV 2021 Scalable Vision Transformers With Hierarchical Pooling ICCV 2021 SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements CVPR 2021 Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU ICCV 2021 Scaling Symbolic Methods using Gradients for Neural Model Explanation ICLR 2021 Scatterbrain: Unifying Sparse and Low-rank Attention NeurIPS 2021 Searching for Alignment in Face Recognition AAAI 2021 Searching for Controllable Image Restoration Networks ICCV 2021 Searching for Fast Model Families on Datacenter Accelerators CVPR 2021 Second-Order Neural ODE Optimizer NeurIPS 2021