Self-Supervised Learning

When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data ACL 2022 When Does Contrastive Visual Representation Learning Work? CVPR 2022 Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations NeurIPS 2022 Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition? Interspeech 2022 Why do We Need Large Batchsizes in Contrastive Learning? A Gradient-Bias Perspective NeurIPS 2022 Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time NeurIPS 2022 Word Discovery in Visually Grounded, Self-Supervised Speech Models Interspeech 2022 Word-wise Sparse Attention for Multimodal Sentiment Analysis Interspeech 2022 Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark NeurIPS 2022 XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale Interspeech 2022 X-model: Improving Data Efficiency in Deep Learning with A Minimax Model ICLR 2022 X-PuDu at SemEval-2022 Task 7: A Replaced Token Detection Task Pre-trained Model with Pattern-aware Ensembling for Identifying Plausible Clarifications SemEval 2022 Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning ICLR 2022 Zero-Shot Aspect-Based Scientific Document Summarization using Self-Supervised Pre-training ACL 2022 Zero-Shot Self-Supervised Learning for MRI Reconstruction ICLR 2022 Zero-Shot Text Classification with Self-Training EMNLP 2022 3D Human Action Representation Learning via Cross-View Consistency Pursuit CVPR 2021 Ab Initio Particle-based Object Manipulation RSS 2021 ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning ICCV 2021 Accelerated Concurrent Learning Algorithms via Data-Driven Hybrid Dynamics and Nonsmooth ODEs L4DC 2021 Accelerating Ecological Sciences from Above: Spatial Contrastive Learning for Remote Sensing AAAI 2021 Accumulative Poisoning Attacks on Real-time Data NeurIPS 2021 ACE: Explaining cluster from an adversarial perspective ICML 2021 A Collective Learning Framework to Boost GNN Expressiveness for Node Classification ICML 2021 A Comparison of Supervised and Unsupervised Pre-Training of End-to-End Models Interspeech 2021