LIMIT23
* *Representation Learning with Very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision
* 360° from a Single Camera: A Few-Shot Approach for LiDAR Segmentation
* Adaptive Self-Training for Object Detection
* Augmenting Features via Contrastive Learning-based Generative Model for Long-Tailed Classification
* Boosting Semi-Supervised Learning by bridging high and low-confidence predictions
* Deep Generative Networks for Heterogeneous Augmentation of Cranial Defects
* Enhancing Classification Accuracy on Limited Data via Unconditional GAN
* FedLID: Self-Supervised Federated Learning for Leveraging Limited Image Data
* Frequency-Aware Self-Supervised Long-Tailed Learning
* G2L: A High-Dimensional Geometric Approach for Automatic Generation of Highly Accurate Pseudo-Labels
* Guiding Video Prediction with Explicit Procedural Knowledge
* Horse with no Labels: Self-Supervised Horse Pose Estimation from Unlabelled Images and Synthetic Prior, A
* Image Guided Inpainting with Parameter Efficient Learning
* JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition
* Learning Universal Semantic Correspondences with No Supervision and Automatic Data Curation
* MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detection
* SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation
* Self-supervised Hypergraphs for Learning Multiple World Interpretations
* Self-training and multi-task learning for limited data: Evaluation study on object detection
* Semantic RGB-D Image Synthesis
* Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection
21 for LIMIT23