Ask the locals: Multi-way local pooling for image recognition

By Y-Lan Boureau, Nicolas Le Roux, Francis R. Bach, Jean Ponce, Yann LeCun. 2011

306 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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 Media Technology

Citations in the corpus

Scattering Networks for Hybrid Representation Learning (2018, methodology): “4 , similar to that reported for the AlexNet ﬁnal layer in [60] and sparse coding with SIFT [8].”
Representation Learning: A Review and New Perspectives (2012, background): “Empirically, the use of pooling seems to contribute significantly to improved classification accuracy in object classification tasks [133], [35], [36].”
A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification (2015, background): “Alternatively, however, pooling may also be performed over small equal sized local regions rather than over the entire feature map (Boureau et al., 2011).”
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree (2015, background): “In the current deep learning literature, popular pooling functions include max, average, and stochastic pooling [3, 2, 40].”
Deep roto-translation scattering for object classification (2014, neutral): “Dict 81.0 Ask the locals [2] Unsup.”
Scaling the Scattering Transform: Deep Hybrid Networks (2017, neutral): “Furthermore, in both case, the SIFT are densely extracted which correspond to approximatively 2 10 4 descriptors, whereas in our case, only 14 2 = 196 scattering coefﬁcients are extracted.”
Beyond spatial pyramids: Receptive field learning for pooled image features (2012, result): “We follow a similar approach to that in [3] to formally define pooled features.”
Learning Semantic Image Representations at a Large Scale (2014, methodology): “We follow a similar approach to that in [12] to formally define pooled features.”
Learning Invariant Feature Hierarchies (2012, background): “In recent months, deep learning systems have broken long-held record on a number of benchmarks in a number of areas including speech recognition [22,23,24], object recognition vision [25,26,27], scene parsing [28], action recognition in video [29,30], natural language processing [31,32], and musical”
Learning Deep Representation for Imbalanced Classification (2016, methodology): “Hence we modify the kNN classifier in two ways: 1) In the well-clustered LMLE space learned in training stage, we treat each cluster as a single class-specific exemplar2, 2Clustering to aid classification is common in the literature [6, 43].”
Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification (2013, background): “Pooling in spatial [25] and feature spaces [6] also lead to higher dimensionality and better performance.”
iCub World: Friendly Robots Help Building Good Vision Data-Sets (2013, methodology): “We briefly review the current state of the art algorithms for visual recognition tasks, with an emphasis on the socalled hierarchical models [14, 24, 3, 18] which have been proved effective on the existing image retrieval benchmarks.”
A survey of deep neural network architectures and their applications (2017, background): “In 2011, Boureau [16] found that even if features are widely dissimilar, it is possible to pool them together as long as their locations are close.”
Learning Discriminative Part Detectors for Image Classification and Cosegmentation (2013, unknown): “5 Multi-way pooling[6] 77 .”
Emergence of Object-Selective Features in Unsupervised Feature Learning (2012, methodology): “[1] use similar intuitions to propose a clustering method similar to our approach.”
Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree (2018, background): “In the current deep learning literature, popular pooling functions include max, average, and stochastic pooling [8], [9], [15].”