Selecting Receptive Fields in Deep Networks

By Adam Coates, Andrew Y. Ng. 2011

233 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Model Architectures

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 Model Architectures

Citations in the corpus

Discriminative Unsupervised Feature Learning with Convolutional Neural Networks (2014, methodology): “Algorithm STL-10 CIFAR-10(400) CIFAR-10 Caltech-101 #features Convolutional K-means Network [27] 60.”
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (2016, background): “The works of [11, 7] introduced the concept of constructing a local receptive field to reduce the number of learned parameters.”
Spectral Networks and Locally Connected Networks on Graphs (2013, methodology): “In [3, 12] the authors estimate similarities between features to construct locally connected networks.”
Deep Convolutional Networks on Graph-Structured Data (2015, background): “There have been several works which have explored architectures using the so-called local receptive ﬁelds [6, 4, 14], mostly with applications to image recognition.”
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (2019, background): “The performances of some state-of-the-art unsupervised methods (k-MeansNet [5], HMP [2], Satck [54] and Exemplar [8]) are also reported.”
Scattering Networks for Hybrid Representation Learning (2018, neutral): “Exemplar CNN [19] 75.4 ± 0.3 Stacked what-where AE [61] 74.33 Hierarchical Matching Pursuit (HMP) [7] 64.5 1 Convolutional K-means Network [13] 60.1 1 We ﬁnd that our model is better in all cases even compared to those utilizing the large unsupervised part of the dataset.”
Predicting Parameters in Deep Learning (2013, background): “Other works have focused on learning receptive fields directly [5], and would be interesting to incorporate with our technique.”
Representation Learning: A Review and New Perspectives (2012, background): “…to generalize feature-pooling so as to learn what features should be pooled together, e.g. as successfully done in several papers (Hyvärinen and Hoyer, 2000; Kavukcuoglu et al., 2009; Le et al., 2010; Ranzato and Hinton, 2010; Courville et al., 2011b; Coates and Ng, 2011b; Gregor et al., 2011).”
Geometric Deep Learning: Going beyond Euclidean data (2016, methodology): “Thus we can replace the original neighborhood structure with one’s favorite multiscale coarsening of the input graph, and operate on that to obtain the same flow of information as with the convolutional nets above (or rather more like a “locally connected network” [81]).”
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree (2015, background): “Learning pooling functions is analogous to receptive field learning [8, 11, 5, 15].”
Convolutional Kernel Networks (2014, neutral): “Method [12] [27] [18] [13] [4] [17] [31] CKN-GM CKN-PM CKN-CO CIFAR-10 82.”
Deep learning for detecting robotic grasps (2013, methodology): “With f ( W ) as a regularization function, weighted by β , and ˆ x ( t ) as the reconstruction of x ( t ) , SAE solves the following to initialize hidden-layer weights: We ﬁrst use this algorithm to initialize W [1] to reconstruct x .”
Joint Unsupervised Learning of Deep Representations and Image Clusters (2016, methodology): “This performance also beats several other methods listed in [4, 15, 25, 34].”
Learning Invariant Representations with Local Transformations (2012, background): “5% deep NN (Coates & Ng, 2011b) 82 .”