← Learning Types
Deep Learning › Learning Types ›

Self-Supervised Learning

2959 directly classified papers

Papers per year

Papers

BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation CVPR 2023
Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images! CVPR 2023
Modeling the Distributional Uncertainty for Salient Object Detection Models CVPR 2023
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale CVPR 2023
Test-time Adaptation with Slot-Centric Models ICML 2023
Multisample Flow Matching: Straightening Flows with Minibatch Couplings ICML 2023
Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach ICML 2023
PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos CVPR 2023
Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation ICML 2023
NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies CVPR 2023
Diffusion Based Representation Learning ICML 2023
Exposing the Self-Supervised Space-Time Correspondence Learning via Graph Kernels AAAI 2023
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations ICML 2023
Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping ICML 2023
Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment CVPR 2023
Dink-Net: Neural Clustering on Large Graphs ICML 2023
Fully Self-Supervised Depth Estimation From Defocus Clue CVPR 2023
Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking CVPR 2023
PATS: Patch Area Transportation With Subdivision for Local Feature Matching CVPR 2023
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN ICML 2023
Generalization Analysis for Contrastive Representation Learning ICML 2023
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning ICML 2023
DPE: Disentanglement of Pose and Expression for General Video Portrait Editing CVPR 2023
DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and Correction CVPR 2023
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation ICML 2023