An Analysis of Single-Layer Networks in Unsupervised Feature Learning

By Adam Coates, Andrew Y. Ng, Honglak Lee. 2011

4,515 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

Pylearn2: a machine learning research library (2013, methodology): “Additionally, there are many kinds of preprocessing, such as PCA [38], ZCA [4], various kinds of local contrast normalization [46], as well as helper functions to set up the entire preprocessing p ipeline from some well-known successful and documented systems [8, 45].”
Learning Transferable Visual Models From Natural Language Supervision (2021, methodology): “These datasets include MNIST, the Facial Expression Recognition 2013 dataset (Goodfellow et al., 2015), STL-10 (Coates et al., 2011), EuroSAT (Helber et al., 2019), the NWPURESISC45 dataset (Cheng et al., 2017), the German Traffic Sign Recognition Benchmark (GTSRB) dataset (Stallkamp et al., 2011),…”
Learning Representations by Maximizing Mutual Information Across Views (2019, methodology): “We evaluate our model using standard datasets: CIFAR10, CIFAR100, STL10 [Coates et al., 2011], ImageNet 1 [Russakovsky et al., 2015], and Places205 [Zhou et al., 2014].”
Contrastive Multiview Coding (2019, methodology): “We measure representation quality by training a linear classifier on the learned representations on the STL-10 dataset [12].”
Do ImageNet Classifiers Generalize to ImageNet? (2019, methodology): “random_features_256k_aug [7] https://github.”
Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces (2017, neutral): “A number of unsupervised algorithms have been proposed to that effect, such as sparse-coding, restricted Boltzmann machines (RBMs), auto-encoders [44], and K-means clustering [4, 8, 20].”
Self-supervised Pretraining of Visual Features in the Wild (2021, methodology): “Selfsupervised learning has a long history in computer vision with methods based on autoencoders [42, 51], clustering [1, 5, 11] or instance-level discrimination [3, 15, 21, 52].”
Discriminative Unsupervised Feature Learning with Convolutional Neural Networks (2014, neutral): “We randomly sampled 500 images from the STL-10 test set and applied a range of transformations (translation, rotation, contrast, color) to each image.”
Spectral Normalization for Generative Adversarial Networks (2018, methodology): “Table 3: Standard CNN models for CIFAR-10 and STL-10 used in our experiments on image Generation.”
Projected GANs Converge Faster (2021, methodology): “We compare on LSUN cat and horse [84], ADE indoor (a subset of ADE [91] proposed in [3]), the full Oxford ﬂowers dataset with 8k images [56], KITTI-ﬁsheye (a subset of KITTI-360 [46], consisting of ﬁsheye images), STL-10 [8], CUB200 [80], Stanford Dogs [36], and Stanford Cars [42].”
Dual Contradistinctive Generative Autoencoder (2020, neutral): “Datasets To validate our method, we train our method on several different datasets — CIFAR-10 [38], STL-10 [10], CelebA [48], CelebA-HQ [34], and LSUN bedroom [67].”
Generating Images with Perceptual Similarity Metrics based on Deep Networks (2016, methodology): “We trained on the STL10 (Coates et al., 2011) unlabeled dataset which contains 100, 000 images 96 × 96 pixels.”
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (2021, neutral): “, 2017), STL10 (Coates et al., 2011) and SUN397 (Xiao et al.”
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (2020, methodology): “Specifically, we perform experiments with varying amounts of labeled data and augmentation strategies on CIFAR10/100 [23], SVHN [35], STL-10 [9], and ImageNet [13], following standard SSL evaluation protocols [36, 4, 3].”
MixMatch: A Holistic Approach to Semi-Supervised Learning (2019, methodology): “STL-10 STL-10 is designed to be used with 10 predeﬁned training set folds with 1000 examples each.”
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (2019, methodology): “[4] is an image recognition dataset with colored images of size 96 × 96 , which is widely used in unsupervised learning.”
Invariant Information Clustering for Unsupervised Image Classification and Segmentation (2018, background): “We perform experiments on a large number of datasets (section 4) including STL, CIFAR, MNIST, COCO-Stuff and Potsdam, setting a new state-of-the-art on unsupervised clustering and segmentation in all cases, with results of 61.0%, 61.7% and 72.3% on STL10, CIFAR10 and COCO-Stuff-3 beating the closest”
Improved Regularization of Convolutional Neural Networks with Cutout (2017, positive): “The STL-10 dataset [3] consists of a total of 113,000 colour images with a resolution of 96 × 96 pixels.”