Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition

By Marc'Aurelio Ranzato, Fu Jie Huang, Y-Lan Boureau. 2008

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

What makes ImageNet good for transfer learning? (2016, background): “The most well-known such criteria are image reconstruction [5, 36, 29, 27, 32, 20] (see [4] for a comprehensive overview) and feature slowness [43, 14].”
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (2019, background): “Bolztmann Machines (RBMs) [24, 40], Auto-encoders [20, 42] and generative adversarial network (GAN) [7, 10, 11] are widely studied.”
Learning to Generate Reviews and Discovering Sentiment (2017, background): “Much of the early research into modern deep learning was developed and validated via this approach (Hinton & Salakhutdinov, 2006) (Huang et al., 2007) (Vincent et al., 2008) (Coates et al., 2010) (Le, 2013).”
Deep Convolutional Inverse Graphics Network (2015, background): “[24], who were amongst the ﬁrst people to use a generic encoder-decoder architecture for feature learning.”
Convolutional Kernel Networks (2014, methodology): “In our paper, we show that a particular convolutional neural network ﬁts well the structure of the convolutional kernel, leading to an approach enjoying classical beneﬁts of CNNs such as efﬁcient prediction at test time.”
Fast and Robust Archetypal Analysis for Representation Learning (2014, unknown): “…K-NN and perform similarly as a non-linear SVM, even though they use a simple Euclidean norm for comparing two digits; (iii) none of the methods in Table 3 exploit the fact that the x i ’s are in fact images, unlike more sophisticated techniques such as convolutional neural networks [22].”
Learning invariant features through topographic filter maps (2009, background): “Much of the recent proposals for object recognition systems are based on feature descriptors extracted from local patches placed at regularly-spaced grid-points on the image [13, 11, 25, 18, 22].”
A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games (2016, background): “…et al., 2015; Wahlstr¨om et al., 2015; Watter et al., 2015; Kingma & Welling, 2014; Rezende et al., 2014; Lange et al., 2012; Hinton et al., 2011; Ranzato et al., 2007), and extends this line of research by showing that autoencoder networks are capable of learning a combined representation for…”
Building high-level features using large scale unsupervised learning (2011, methodology): “Our work is inspired by recent successful algorithms in unsupervised feature learning and deep learning (Hin-ton et al., 2006; Bengio et al., 2007; Ranzato et al., 2007; Lee et al., 2007).”