Fetching the paper…

Reading the bibliography…

2020

Empirical Perspectives on One-Shot Semi-supervised Learning

Smith, Leslie N., Conovaloff, Adam

Original
PDF
Post on X

Understand

One of the greatest obstacles in the adoption of deep neural networks for new applications is that training the network typically requires a large number of manually labeled training samples.

We empirically investigate the scenario where one has access to large amounts of unlabeled data but require labeling only a single prototypical sample per class in order to train a deep network (i.e., one-shot semi-supervised learning).
Specifically, we investigate the recent results reported in FixMatch for one-shot semi-supervised learning to understand the factors that affect and impede high accuracies and reliability for one-shot semi-supervised learning of Cifar-10.
For example, we discover that one barrier to one-shot semi-supervised learning for high-performance image classification is the unevenness of class accuracy during the training.

Empirical Perspectives on One-Shot Semi-supervised Learning · Around

Built on

Self-training with noisy student improves imagenet classification
Original
Qizhe Xie, Eduard Hovy, Minh-Thang Luong, and Quoc V Le · 2004
Earlier work this paper cites.
Learning multiple layers of features from tiny images
Alex Krizhevsky, Geoffrey Hinton, et al · 2009
Earlier work this paper cites.
Siamese neural networks for one-shot image recognition
Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov · 2015
Earlier work this paper cites.
Matching networks for one shot learning
Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra, et al · 2016
Earlier work this paper cites.
Improved regularization of convolutional neural networks with cutout
Original
Terrance DeVries and Graham W Taylor · 2017
Earlier work this paper cites.

Similar

Model-agnostic meta-learning for fast adaptation of deep networks
Chelsea Finn, Pieter Abbeel, and Sergey Levine · 2017
Cited alongside, same era.
Focal loss for dense object detection
Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár · 2017
Cited alongside, same era.
Prototypical networks for few-shot learning
Jake Snell, Kevin Swersky, and Richard Zemel · 2017
Cited alongside, same era.
Unsupervised learning via meta-learning
Original
Kyle Hsu, Sergey Levine, and Chelsea Finn · 2018
Cited alongside, same era.
Image classification with deep learning in the presence of noisy labels: A survey
Original
Görkem Algan and Ilkay Ulusoy · 2019
Cited alongside, same era.

Then

Assume, augment and learn: Unsupervised few-shot meta-learning via random labels and data augmentation
Original
Antreas Antoniou and Amos Storkey · 2019
Later among the works it cites.
Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring
Original
David Berthelot, Nicholas Carlini, Ekin D Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, and Colin Raffel · 2019
Later among the works it cites.
Randaugment: Practical data augmentation with no separate search
Original
Ekin D Cubuk, Barret Zoph, Jonathon Shlens, and Quoc V Le · 2019
Later among the works it cites.
Survey on deep learning with class imbalance
Justin M Johnson and Taghi M Khoshgoftaar · 2019
Later among the works it cites.
Fixmatch: Simplifying semi-supervised learning with consistency and confidence
Original

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D Cubuk, Alex Kurakin, Han Zhang, and Colin Raffel · 2020

Closest in time.