Data Augmentation

HypMix: Hyperbolic Interpolative Data Augmentation EMNLP 2021 Improved Handling of Motion Blur in Online Object Detection CVPR 2021 Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation AAAI 2021 Improving Label Noise Robustness with Data Augmentation and Semi-Supervised Learning (Student Abstract) AAAI 2021 Improving Panoptic Segmentation at All Scales CVPR 2021 Joint-Label Learning by Dual Augmentation for Time Series Classification AAAI 2021 KeepAugment: A Simple Information-Preserving Data Augmentation Approach CVPR 2021 Kernel-convoluted Deep Neural Networks with Data Augmentation AAAI 2021 LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active Learning NeurIPS 2021 LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification ACL 2021 Learning Data Augmentation Schedules for Natural Language Processing EMNLP 2021 Learning Debiased Representation via Disentangled Feature Augmentation NeurIPS 2021 Learning to Recombine and Resample Data For Compositional Generalization ICLR 2021 LiDAR-Aug: A General Rendering-Based Augmentation Framework for 3D Object Detection CVPR 2021 LIREx: Augmenting Language Inference with Relevant Explanations AAAI 2021 MetaAugment: Sample-Aware Data Augmentation Policy Learning AAAI 2021 MODALS: Modality-agnostic Automated Data Augmentation in the Latent Space ICLR 2021 Model Patching: Closing the Subgroup Performance Gap with Data Augmentation ICLR 2021 Multilingual Paraphrase Generation For Bootstrapping New Features in Task-Oriented Dialog Systems EMNLP 2021 Negative Data Augmentation ICLR 2021 On Feature Normalization and Data Augmentation CVPR 2021 On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise EMNLP 2021 Physics-constrained Automatic Feature Engineering for Predictive Modeling in Materials Science AAAI 2021 PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation CVPR 2021 Privacy-Preserving Collaborative Learning With Automatic Transformation Search CVPR 2021