Self-Supervised Learning

Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis CVPR 2022 Autoregressive Co-Training for Learning Discrete Speech Representation Interspeech 2022 AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels NeurIPS 2022 AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis CVPR 2022 Backdoor Attacks on Self-Supervised Learning CVPR 2022 Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images AAAI 2022 BEVT: BERT Pretraining of Video Transformers CVPR 2022 Beyond Learning Features: Training a Fully-Functional Classifier with ZERO Instance-Level Labels AAAI 2022 Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations NeurIPS 2022 BioLORD: Learning Ontological Representations from Definitions for Biomedical Concepts and their Textual Descriptions EMNLP 2022 Blind2Unblind: Self-Supervised Image Denoising With Visible Blind Spots CVPR 2022 Boosting Active Learning via Improving Test Performance AAAI 2022 Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings EMNLP 2022 Bridging the Gap between Recognition-level Pre-training and Commonsensical Vision-language Tasks ACL 2022 Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning NeurIPS 2022 Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech AAAI 2022 Bridging Video-Text Retrieval With Multiple Choice Questions CVPR 2022 BYOL-Explore: Exploration by Bootstrapped Prediction NeurIPS 2022 Can Semantic Labels Assist Self-Supervised Visual Representation Learning? AAAI 2022 Can Vision Transformers Learn without Natural Images? AAAI 2022 CAPRI-Net: Learning Compact CAD Shapes With Adaptive Primitive Assembly CVPR 2022 CASA: Category-agnostic Skeletal Animal Reconstruction NeurIPS 2022 CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data NAACL 2022 CETA: A Consensus Enhanced Training Approach for Denoising in Distantly Supervised Relation Extraction COLING 2022 Chitransformer: Towards Reliable Stereo From Cues CVPR 2022