Sign in
Meta learning / Few-shot Learning
Apr 6, 2021
32 videos
Share
Watch
Most Popular
Most Recent
Watch later
3:01
[NeurIPS 2020] Gradient-EM Bayesian Meta-Learning
Yayi Zou
Watch later
0:56
When Does Self-supervision Improve Few-shot Learning?
Jong-Chyi Frederick Su
Watch later
9:56
[ECCV 2020] Graph convolutional networks for learning with few clean and many noisy labels
Giorgos Tolias
Watch later
11:28
Meta-DermDiagnosis: Few-Shot Skin Disease Identification Using Meta-Learning
ComputerVisionFoundation Videos
Watch later
0:57
MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment
ComputerVisionFoundation Videos
Watch later
4:54
[KDD 2020] TAdaNet: Task-Adaptive Network for Graph-Enriched Meta-Learning
Qiuling Suo
Watch later
1:01
Learning to Learn Single Domain Generalization
ComputerVisionFoundation Videos
Watch later
0:47
M2SGD: Learning to Learn Important Weights
ComputerVisionFoundation Videos
Watch later
5:01
Learning Meta Face Recognition in Unseen Domains
ComputerVisionFoundation Videos
Watch later
4:51
Covariate Distribution Aware Meta-Learning, Lifelong Learning Workshop, ICML 2020
Saket Dingliwal
Watch later
5:02
Meta-Learning of Neural Architectures for Few-Shot Learning
ComputerVisionFoundation Videos
Watch later
0:59
Meta-Transfer Learning for Zero-Shot Super-Resolution
ComputerVisionFoundation Videos
Watch later
1:04
Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions
ComputerVisionFoundation Videos
Watch later
1:01
TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning
ComputerVisionFoundation Videos
Watch later
5:00
Tracking by Instance Detection: A Meta-Learning Approach
ComputerVisionFoundation Videos
Watch later
1:01
Few-Shot Open-Set Recognition Using Meta-Learning
ComputerVisionFoundation Videos
Watch later
0:55
Scene-Adaptive Video Frame Interpolation via Meta-Learning
ComputerVisionFoundation Videos
Watch later
1:01
iTAML: An Incremental Task-Agnostic Meta-learning Approach
ComputerVisionFoundation Videos
Watch later
5:51
Meta-Learning via Learned Loss | ICPR 2020 Best Student Paper
Sarah Bechtle
Watch later
1:01
Few-Shot Learning of Part-Specific Probability Space for 3D Shape Segmentation
ComputerVisionFoundation Videos
Watch later
1:00
DPGN: Distribution Propagation Graph Network for Few-Shot Learning
ComputerVisionFoundation Videos
Watch later
1:01
Boosting Few-Shot Learning With Adaptive Margin Loss
ComputerVisionFoundation Videos
Watch later
1:01
Attentive Weights Generation for Few Shot Learning via Information Maximization
ComputerVisionFoundation Videos
Watch later
1:01
Adversarial Feature Hallucination Networks for Few-Shot Learning
ComputerVisionFoundation Videos
Watch later
1:01
Instance Credibility Inference for Few-Shot Learning
ComputerVisionFoundation Videos
Watch later
5:00
Taming the Herd: Multi-Modal Meta-Learning with a Population of Agents
Robert Mueller
Watch later
1:01
Sequential Mastery of Multiple Visual Tasks: Networks Naturally Learn to Learn and Forget to Forget
ComputerVisionFoundation Videos
Watch later
1:01
Adaptive Subspaces for Few-Shot Learning
ComputerVisionFoundation Videos
Watch later
1:01
Training Noise-Robust Deep Neural Networks via Meta-Learning
ComputerVisionFoundation Videos
Watch later
1:01
Multi-Domain Learning for Accurate and Few-Shot Color Constancy
ComputerVisionFoundation Videos
Watch later
5:01
Few-Shot Class-Incremental Learning
ComputerVisionFoundation Videos
Watch later
0:58
Semi-Supervised Learning for Few-Shot Image-to-Image Translation
ComputerVisionFoundation Videos
