RenderGAN: Generating Realistic Labeled Data

Sixt, Leon; Wild, Benjamin; Landgraf, Tim

doi:10.48550/arxiv.1611.01331

Cited by 17 publications

(20 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, generative adversarial networks (GAN) have been used to choose optimal sequences of data augmentation operations [39]. GANs have also been used to generate training data directly [37,33,56,1,44], however this approach does not seem to be as beneficial as learning sequences of data augmentation operations that are pre-defined [40].…”

Section: Related Workmentioning

confidence: 99%

RandAugment: Practical automated data augmentation with a reduced search space

Cubuk¹,

Zoph²,

Shlens³

et al. 2019

Preprint

108

View full text Add to dashboard Cite

Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and object detection. While these strategies were optimized for improving validation accuracy, they also led to state-of-the-art results in semi-supervised learning and improved robustness to common corruptions of images. An obstacle to a large-scale adoption of these methods is a separate search phase which increases the training complexity and may substantially increase the computational cost. Additionally, due to the separate search phase, these approaches are unable to adjust the regularization strength based on model or dataset size. Automated augmentation policies are often found by training small models on small datasets and subsequently applied to train larger models. In this work, we remove both of these obstacles. RandAugment has a significantly reduced search space which allows it to be trained on the target task with no need for a separate proxy task. Furthermore, due to the parameterization, the regularization strength may be tailored to different model and dataset sizes. RandAugment can be used uniformly across different tasks and datasets and works out of the box, matching or surpassing all previous automated augmentation approaches on CIFAR-10/100, SVHN, and ImageNet. On the ImageNet dataset we achieve 85.0% accuracy, a 0.6% increase over the previous state-of-the-art and 1.0% increase over baseline augmentation. On object detection, RandAugment leads to 1.0-1.3% improvement over baseline augmentation, and is within 0.3% mAP of AutoAugment on COCO. Finally, due to its interpretable hyperparameter, RandAugment may be used to investigate the role of data augmentation with varying model and dataset size. Code is available online. 1 * Authors contributed equally.1 github.com/tensorflow/tpu/tree/master/models/ official/efficientnet

show abstract

Section: Related Workmentioning

confidence: 99%

RandAugment: Practical automated data augmentation with a reduced search space

Cubuk¹,

Zoph²,

Shlens³

et al. 2019

Preprint

108

View full text Add to dashboard Cite

show abstract

“…Recent work has shown that instead of manually designing data augmentation strategies, learning an optimal policy from data can lead to significant improvements in generalization performance of image classification models [22,45,8,33,31,54,2,43,37,5]. For image classification models, data can be augmented either by learning a generator that can create data from scratch [33,31,54,2,43], or by learning a set of transformations as applied to already existing training set samples [5,37]. For object detection models, the need for data augmentation is more crucial as collecting labeled data for detection is more costly and common detection datasets have many fewer examples than image classification datasets.…”

Section: Introductionmentioning

confidence: 99%

Learning Data Augmentation Strategies for Object Detection

Zoph¹,

Cubuk²,

Ghiasi³

et al. 2019

Preprint

View full text Add to dashboard Cite

Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential has not been thoroughly investigated for object detection. Given the additional cost for annotating images for object detection, data augmentation may be of even greater importance for this computer vision task. In this work, we study the impact of data augmentation on object detection. We first demonstrate that data augmentation operations borrowed from image classification may be helpful for training detection models, but the improvement is limited. Thus, we investigate how learned, specialized data augmentation policies improve generalization performance for detection models. Importantly, these augmentation policies only affect training and leave a trained model unchanged during evaluation. Experiments on the COCO dataset indicate that an optimized data augmentation policy improves detection accuracy by more than +2.3 mAP, and allow a single inference model to achieve a state-of-the-art accuracy of 50.7 mAP. Importantly, the best policy found on COCO may be transferred unchanged to other detection datasets and models to improve predictive accuracy. For example, the best augmentation policy identified with COCO improves a strong baseline on PASCAL-VOC by +2.7 mAP. Our results also reveal that a learned augmentation policy is superior to state-of-the-art architecture regularization methods for object detection, even when considering strong baselines. Code for training with the learned policy is available online. 1 * Equal contribution.1 github.com/tensorflow/tpu/tree/master/models/ official/detection

show abstract

“…Two years later, AlexNet spoke volumes in support of the importance scale of data. For recent representative works in increasing data scale via synthetic data or unlabeled data, please consult [32,48,51,56,59].…”

Section: Discussionmentioning

confidence: 99%

Representation Learning on Large and Small Data

Chou¹,

Shie²,

Chang³

et al. 2019

Big Data Analytics for Large‐Scale Multimedia Search

View full text Add to dashboard Cite

Extracting useful features from a scene is an essential step in any computer vision and multimedia data analysis task. Though progress has been made in past decades, it is still quite difficult for computers to comprehensively and accurately recognize an object or pinpoint the more complicated semantics of an image or a video. Thus, feature extraction is expected to remain an active research area in advancing computer vision and multimedia data analysis for the foreseeable future.The approaches in feature extraction can be divided into two categories: model-centric and datadriven. The model-centric approach relies on human heuristics to develop a computer model (or algorithm) to extract features from an image. (We use imagery data as our example throughout this chapter.) Some widely used models are Gabor filter, wavelets, and SIFT [42]. These models were engineered by scientists and then validated via empirical studies. A major shortcoming of the model-centric approach is that unusual circumstances that a model does not take into consideration during its design, such as different lighting conditions and unexpected environmental factors, can render the engineered features less effective. Contrast to the model-centric approach, which dictates representations independent of data, the data-driven approach learns representations from data [10]. Example data-driven algorithms are multilayer perceptron (MLP) and convolutional neural network (CNN), which belong to the general category of neural network and deep learning [27,29].Both model-centric and data-driven approaches employ a model (algorithm or machine). The differences between model-centric and data-driven can be told in two related aspects:• Can data affect model parameters? With model-centric, training data does not affect the model. With data-driven, such as MLP or CNN, their internal parameters are changed/learned based on the discovered structure in large data sets [38].• Can data affect representations? Whereas more data can help a data-driven approach to improve representations, more data cannot change the features extracted by a model-centric approach. For example, the features of an image can be affected by the other images in CNN (because the structure parameters modified through backpropagation are affected by all training images). But the feature set of an image is invariant of the other images in a model-centric pipeline such as SIFT.The greater the quantity and diversity of data, the better the representations can be learned by a data-driven pipeline. In other words, if a learning algorithm has seen enough training instances of an object under various conditions, e.g., in different postures and has been partially occluded, then the features learned from the training data will be more comprehensive. The focus of this chapter is on how neural network, specifically convolutional neural network (CNN), achieves effective representation learning. Neural network, a neuroscience-motivated model, was based on Hubel and Wiesel's research on cats' visual corte...

show abstract

RenderGAN: Generating Realistic Labeled Data

Cited by 17 publications

References 0 publications

RandAugment: Practical automated data augmentation with a reduced search space

RandAugment: Practical automated data augmentation with a reduced search space

Learning Data Augmentation Strategies for Object Detection

Representation Learning on Large and Small Data

Contact Info

Product

Resources

About