Unsupervised Data Augmentation

By Qizhe Xie, Zihang Dai, Eduard H. Hovy, Minh-Thang Luong, Quoc V. Le. 2019

219 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

A Simple Framework for Contrastive Learning of Visual Representations (2020, background): “A similar consistency idea has been explored in other contexts such as semi-supervised learning (Xie et al., 2019; Berthelot et al., 2019).”
Data-Efficient Image Recognition with Contrastive Predictive Coding (2019, background): “The predictions of this classifier are often constrained to be smooth with respect to certain deformations, such as data-augmentation (Xie et al., 2019) or adversarial perturbation (Miyato et al.”
S4L: Self-Supervised Semi-Supervised Learning (2019, neutral): “Recent concurrent work [40, 12] presents competitive results on ILSVRC-2012.”
Big Self-Supervised Models are Strong Semi-Supervised Learners (2020, methodology): “Another family of methods are based on label consistency regularization [55–58, 14, 13, 59, 15], where unlabeled examples are directly used as a regularizer to encourage task prediction consistency.”
Randaugment: Practical automated data augmentation with a reduced search space (2019, methodology): “Training a machine learning model with a learned data augmentation policy may significantly improve image classification [4, 19, 15], object detection [51], model robustness [25, 46, 34], and semi-supervised learning image classification [44].”
Self-Supervised Learning of Pretext-Invariant Representations (2019, methodology): “PIRL is most similar to methods that learn representations that are invariant under standard data augmentation [4, 14, 29, 31, 81, 82].”
Revisiting Self-Training for Neural Sequence Generation (2019, neutral): “These approaches have been very successful on classiﬁcation tasks (Rasmus et al., 2015; Miyato et al., 2017; Laine & Aila, 2017; Miyato et al., 2018; Xie et al., 2019) given that a reasonable amount of predictions of unlabeled data (at least the ones with high conﬁdence) are correct, but their…”
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty (2019, background): “The Jensen-Shannon Consistency Loss impels to model to be stable, consistent, and insensitive across to a diverse range of inputs (Zheng et al., 2016; Kannan et al., 2018; Xie et al., 2019).”
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation (2019, background): “assiﬁers. [27, 28] use GANs to modify the outputs of simulators to look like real objects. Automating data augmentation can also be applied to representation learning such as semi-supervised learning [4, 33] and domain generalization [32]. 3. Preliminaries In this section, we describe the common bas”
Unlabeled Data Improves Adversarial Robustness (2019, background): “In the low-data/standard accuracy regime, strong data augmentation is competitive against and complementary to semisupervised learning [10, 51], as it effectively increases the sample size by generating different plausible inputs.”
Are Labels Required for Improving Adversarial Robustness? (2019, methodology): “14 [50] Q.”
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation (2019, background): “Recent work in this area includes learning better transformations [9, 52, 53], inferring combinations of transformations [6], unsupervised methods [49], theory of data augmentation [7], and applications for one-shot learning [1].”
Selfie: Self-supervised Pretraining for Image Embedding (2019, methodology): “For example, the recent Unsupervised Data Augmentation (Xie et al., 2019) reported 94.7% accuracy on the 8% subset of CIFAR-10.”
Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, background): “As seen in Figure 1, the recent works based on neural architectures (Le & Mikolov, 2014; Dai & Le, 2015; Johnson & Zhang, 2016; Miyato et al., 2017; McCann et al., 2017; Howard & Ruder, 2018; Xie et al., 2019; Thongtan & Phienthrakul, 2019) have dominated over traditional machine learning models (Ma”
Contextual Explanation Networks (2017, background): “We also remark that classifiers derived from large-scale language models pretrained on massive unsupervised corpora (e.g., Gray et al., 2017; Howard and Ruder, 2018; Xie et al., 2019) have become popular and now dominate the leaderboard for this task.”
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness (2019, methodology): “These approaches are based on augmenting the training data either statically [17, 30, 7, 45], ie.”
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning (2019, unknown): “, 2018) and unsupervised learning (Salimans et al., 2016; Xie et al., 2019).”