• Publications
  • Influence
MixMatch: A Holistic Approach to Semi-Supervised Learning
TLDR
This work unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that works by guessing low-entropy labels for data-augmented unlabeled examples and mixing labeled and unlabeling data using MixUp.
Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
TLDR
This work creates a unified reimplemention and evaluation platform of various widely-used SSL techniques and finds that the performance of simple baselines which do not use unlabeled data is often underreported, that SSL methods differ in sensitivity to the amount of labeled and unlabeling data, and that performance can degrade substantially when the unlabelED dataset contains out-of-class examples.
S4L: Self-Supervised Semi-Supervised Learning
TLDR
It is shown that S4L and existing semi-supervised methods can be jointly trained, yielding a new state-of-the-art result on semi- supervised ILSVRC-2012 with 10% of labels.
Realistic Evaluation of Semi-Supervised Learning Algorithms
TLDR
This work creates a unified reimplemention and evaluation platform of various widelyused SSL techniques and finds that the performance of simple baselines which do not use unlabeled data is often underreported, that SSL methods differ in sensitivity to the amount of labeled and unlabeling data, and that performance can degrade substantially when the unlabelED dataset contains out-of-class examples.
Teacher–Student Curriculum Learning
We propose Teacher–Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task, and the Teacher automatically chooses subtasks
MetNet: A Neural Weather Model for Precipitation Forecasting
TLDR
This work introduces MetNet, a neural network that forecasts precipitation up to 8 hours into the future at the high spatial resolution of 1 km$^2$ and at the temporal resolution of 2 minutes with a latency in the order of seconds, and finds that MetNet outperforms Numerical Weather Prediction at forecasts of up to 7 to8 hours on the scale of the continental United States.
When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasets
TLDR
This study comprehensively study how SSL methods starting from pretrained models perform under varying conditions, including training strategies, architecture choice and datasets, and demonstrates that the gains from SSL techniques over a fully-supervised baseline are smaller when training from a pre-trained model than when trained from random initialization.
Milking CowMask for Semi-Supervised Image Classification
TLDR
A novel mask-based augmentation method called CowMask is presented, using it to provide perturbations for semi-supervised consistency regularization, which achieves a state-of-the-art result on ImageNet with 10% labeled data.
S$^\mathbf{4}$L: Self-Supervised Semi-Supervised Learning
TLDR
This work proposes the framework of self-supervised semi- Supervised learning ($S^4L$) and uses it to derive two novel semi- supervised image classification methods and demonstrates the effectiveness of these methods in comparison to both carefully tuned baselines, and existing semi-super supervised learning methods.
Model AI Assignments 2020
The Model AI Assignments session seeks to gather and disseminate the best assignment designs of the Artificial Intelligence (AI) Education community. Recognizing that assignments form the core of
...
1
2
...