Learning Multiple Layers of Features from Tiny Images

By Alex Krizhevsky. 2009

43,276 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Deep Residual Learning for Image Recognition (2015, methodology): “We conducted more studies on the CIFAR-10 dataset [20], which consists of 50k training images and 10k testing images in 10 classes.”
Generative Adversarial Nets (2014, methodology): “We trained adversarial nets an a range of datasets including MNIST[23], the Toronto Face Database (TFD) [28], and CIFAR-10 [21].”
Semi-Supervised Sequence Modeling with Cross-View Training (2018, methodology): “Therefore we see much better results from VAT on semi-supervised CIFAR-10 compared to on our NLP tasks.”
FitNets: Hints for Thin Deep Nets (2014, methodology): “Experiments are performed on CIFAR-10 dataset (Krizhevsky & Hinton, 2009).”
Microsoft COCO: Common Objects in Context (2014, background): “Popular datasets in the machine learning community due to the larger number of training examples, CIFAR-10 and CIFAR-100 [27] offered 10 and 100 categories from a dataset of tiny 32 × 32 images [28].”
Network In Network (2013, methodology): “The CIFAR-100 dataset [12] is the same in size and format as the CIFAR-10 dataset, but it contains 100 classes.”
Maxout Networks (2013, methodology): “The CIFAR-10 dataset (Krizhevsky & Hinton, 2009) consists of 32 × 32 color images drawn from 10 classes split into 50,000 train and 10,000 test images.”
Improving neural networks by preventing co-adaptation of feature detectors (2012, methodology): “These images were labeled by hand to produce 50,000 training images and 10,000 test images in which there is a single dominant object that could plausibly be given the class name [11] (see figure 2).”
No more pesky learning rates (2012, methodology): “We choose two widely used standard datasets to test the diﬀerent algorithms; the MNIST digit recognition dataset (LeCun & Cortes, 1998) (with 60k training samples, and 10k test samples), and the CIFAR-10 small natural image dataset (Krizhevsky, 2009) Table 3.”
Pylearn2: a machine learning research library (2013, methodology): “These include the datasets used for DARPA’s unsupervised and transfer learning challenge [25] , the dataset used for the NIPS 2011 workshops challenge in representation learning [32], the C IFAR-10 and CIFAR-100 datasets [29], the MNIST dataset [34], some of the MNIST variations dataset s [31], the ”
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (2020, methodology): “, 2020), CIFAR-10/100 (Krizhevsky, 2009), Oxford-IIIT Pets (Parkhi et al.”
A Simple Framework for Contrastive Learning of Visual Representations (2020, positive): “The best self-supervised model that reports linear evaluation result on CIFAR-10 is AMDIM (Bachman et al., 2019), which achieves 91.2% with a model 25 × larger than ours.”
Unsupervised Data Augmentation for Consistency Training (2019, methodology): “Firstly, as shown in Table 6, if we apply the augmentation policy found on SVHN by AutoAugment to CIFAR-10 (denoted by Switched Augment), the error rate increases from 5 .”
Learning to learn by gradient descent by gradient descent (2016, methodology): “Next we test the performance of the trained neural optimizers on optimizing classiﬁcation performance for the CIFAR-10 dataset [Krizhevsky, 2009].”
Measuring the Effects of Data Parallelism on Neural Network Training (2018, background): “10 Keskar et al. (2017) trained several neural network architectures on MNIST and CIFAR-10, each with two batch sizes, using the Adam optimizer and without changing the learning rate between batch sizes.”
Do Better ImageNet Models Transfer Better? (2018, background): “All datasets had a median image size on the shortest side of at least 331 pixels (the highest input image size out of all networks tested), except Caltech-101, for which the median size is 225 on the shortest side and 300 on the longer side, and CIFAR-10 and CIFAR-100, which consist of 32× 32 pixel ”
Federated Learning: Strategies for Improving Communication Efficiency (2016, methodology): “We conducted the experiments using federated learning to train deep neural networks for the CIFAR10 image classification task [10].”
Gaussian Error Linear Units (GELUs) (2016, methodology): “We evaluate this activation function using CIFAR-10 and CIFAR-100 datasets (Krizhevsky, 2009) on shallow and deep convolutional neural networks, respectively.”