Self-Supervised Learning

Object-Centric Multiple Object Tracking ICCV 2023 Object Detection With Self-Supervised Scene Adaptation CVPR 2023 ObjectStitch: Object Compositing With Diffusion Model CVPR 2023 Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching AAAI 2023 OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis CVPR 2023 On Data Scaling in Masked Image Modeling CVPR 2023 On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation Interspeech 2023 OneFormer: One Transformer To Rule Universal Image Segmentation CVPR 2023 One-Model-Connects-All: A Unified Graph Pre-Training Model for Online Community Modeling EMNLP 2023 One-to-Few Label Assignment for End-to-End Dense Detection CVPR 2023 On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation Learning ACL 2023 Online Noisy Continual Relation Learning AAAI 2023 On Masked Pre-training and the Marginal Likelihood NeurIPS 2023 On Separate Normalization in Self-supervised Transformers NeurIPS 2023 On the Benefits of Self-supervised Learned Speech Representations for Predicting Human Phonetic Misperceptions Interspeech 2023 On the Correspondence between Compositionality and Imitation in Emergent Neural Communication ACL 2023 On the duality between contrastive and non-contrastive self-supervised learning ICLR 2023 On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning. ICLR 2023 On the Effects of Self-Supervision and Contrastive Alignment in Deep Multi-View Clustering CVPR 2023 On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning ICML 2023 On the (In)Efficiency of Acoustic Feature Extractors for Self-Supervised Speech Representation Learning Interspeech 2023 On the Power of Foundation Models ICML 2023 On the Robustness of Arabic Speech Dialect Identification Interspeech 2023 On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion ICCV 2023 On the Stepwise Nature of Self-Supervised Learning ICML 2023