Model Architecture

Robust Training in High Dimensions via Block Coordinate Geometric Median Descent AISTATS 2022 Robust Training of Neural Networks Using Scale Invariant Architectures ICML 2022 Robust Weight Perturbation for Adversarial Training IJCAI 2022 ROLLER: Fast and Efficient Tensor Compilation for Deep Learning OSDI 2022 RRED : A Radiology Report Error Detector based on Deep Learning Framework NAACL 2022 S2-MLP: Spatial-Shift MLP Architecture for Vision WACV 2022 S4ND: Modeling Images and Videos as Multidimensional Signals with State Spaces NeurIPS 2022 Saliency-Aware Neural Architecture Search NeurIPS 2022 Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing AAAI 2022 Sample and Computation Redistribution for Efficient Face Detection ICLR 2022 Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy NeurIPS 2022 Scaled ReLU Matters for Training Vision Transformers AAAI 2022 Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework ICML 2022 Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs CVPR 2022 SE(2)-Equivariant Pushing Dynamics Models for Tabletop Object Manipulations CoRL 2022 Searching for Better Spatio-temporal Alignment in Few-Shot Action Recognition NeurIPS 2022 Searching for BurgerFormer with Micro-Meso-Macro Space Design ICML 2022 Searching the Deployable Convolution Neural Networks for GPUs CVPR 2022 Secure Distributed Training at Scale ICML 2022 SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation NeurIPS 2022 Self-Distillation Based on High-level Information Supervision for Compressing End-to-End ASR Model Interspeech 2022 Self-ensemble Adversarial Training for Improved Robustness ICLR 2022 Self-explaining deep models with logic rule reasoning NeurIPS 2022 Semantic Diffusion Network for Semantic Segmentation NeurIPS 2022 SGAT: Simplicial Graph Attention Network IJCAI 2022