Techniques

Noise Attention Learning: Enhancing Noise Robustness by Gradient Scaling NeurIPS 2022 NoiseGrad — Enhancing Explanations by Introducing Stochasticity to Model Weights AAAI 2022 Noisy Feature Mixup ICLR 2022 NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models Better ACL 2022 Non-deep Networks NeurIPS 2022 Not All Bits have Equal Value: Heterogeneous Precisions via Trainable Noise NeurIPS 2022 ObjectFormer for Image Manipulation Detection and Localization CVPR 2022 Objective Metrics to Evaluate Residual-Echo Suppression During Double-Talk in the Stereophonic Case Interspeech 2022 Occlusion-Robust Face Alignment Using a Viewpoint-Invariant Hierarchical Network Architecture CVPR 2022 OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression AAAI 2022 OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework ICML 2022 Omni-Dimensional Dynamic Convolution ICLR 2022 OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering NAACL 2022 On-demand compute reduction with stochastic wav2vec 2.0 Interspeech 2022 One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks EMNLP 2022 Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking IJCAI 2022 Online-Updated High-Order Collaborative Networks for Single Image Deraining AAAI 2022 On Masked Language Models for Contextual Link Prediction ACL 2022 On Redundancy and Diversity in Cell-based Neural Architecture Search ICLR 2022 On-the-fly ASR Corrections with Audio Exemplars Interspeech 2022 On the Frequency-bias of Coordinate-MLPs NeurIPS 2022 On the Integration of Self-Attention and Convolution CVPR 2022 On the Locality of Attention in Direct Speech Translation ACL 2022 On the non-universality of deep learning: quantifying the cost of symmetry NeurIPS 2022 On the Practicality of Deterministic Epistemic Uncertainty ICML 2022