Model Architecture

A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels ICLR 2021 A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness NeurIPS 2021 Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks ICML 2021 BASE Layers: Simplifying Training of Large, Sparse Models ICML 2021 BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer NeurIPS 2021 Bayesian Nested Neural Networks for Uncertainty Calibration and Adaptive Compression CVPR 2021 BCNet: Searching for Network Width With Bilaterally Coupled Network CVPR 2021 Benchmarking Ultra-High-Definition Image Super-Resolution ICCV 2021 Benefits of Linear Conditioning for Segmentation using Metadata MIDL 2021 BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation NeurIPS 2021 BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks ACL 2021 Better Training using Weight-Constrained Stochastic Dynamics ICML 2021 Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters ICLR 2021 BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification CVPR 2021 Boost Neural Networks by Checkpoints NeurIPS 2021 BoW Pooling: A Plug-and-Play Unit for Feature Aggregation of Point Clouds AAAI 2021 BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction ICLR 2021 BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization ICLR 2021 Building Interpretable Interaction Trees for Deep NLP Models AAAI 2021 CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks AAAI 2021 CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings NeurIPS 2021 Catformer: Designing Stable Transformers via Sensitivity Analysis ICML 2021 CDFI: Compression-Driven Network Design for Frame Interpolation CVPR 2021 ChartOCR: Data Extraction From Charts Images via a Deep Hybrid Framework WACV 2021 Chasing Sparsity in Vision Transformers: An End-to-End Exploration NeurIPS 2021