Efficient learning of sparse, distributed, convolutional feature representations for object recognition

By Kihyuk Sohn, Dae Yon Jung, Honglak Lee, A. Hero. 2011

135 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Sergey Levine
2. Dieter Fox
3. Honglak Lee
4. Trevor Darrell
5. G. Wang
6. Percy Liang
7. Yoshua Bengio
8. Pieter Abbeel

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Xiaogang Wang
3. Ming-Hsuan Yang
4. Dacheng Tao
5. Jitendra Malik
6. Yi Yang
7. Trevor Darrell
8. Andrea Vedaldi

In Representation & Self-Supervised Learning

1. Matthew D. Zeiler
2. Liefeng Bo
3. Dieter Fox
4. Xiaofeng Ren
5. Honglak Lee
6. Kihyuk Sohn
7. Guanyu Zhou
8. Chansoo Lee

Citations in the corpus

• Visualizing and Understanding Convolutional Networks (2013, neutral): “Acc % Acc % Acc % Acc % # Train 15/class 30/class 45/class 60/class (Sohn et al., 2011) 35.”
• Learning Invariant Representations with Local Transformations (2012, methodology): “Specifically, convolutional training (LeCun et al., 1989; Kavukcuoglu et al., 2010; Zeiler et al., 2010; Lee et al., 2011; Sohn et al., 2011) is one of the most popular methods that encourages shift-invariance during the feature learning.”
• Multipath Sparse Coding Using Hierarchical Matching Pursuit (2013, methodology): “SIFT+T [9] is soft threshold coding and CRBM [27] is a convolutional variant of Restricted Boltzmann Machines (RBM).”
• Learning hierarchical representations for face verification with convolutional deep belief networks (2012, background): “For more details of the overall training procedure, see [17, 34].”
• Deep learning for robust feature generation in audiovisual emotion recognition (2013, background): “Unsupervised Feature Learning and Deep Learning Deep learning techniques (See [9] for a survey) have become increasingly popular in various communities including speech and language processing [10] [11] [12] and vision processing [26] [27] [28] [29] [30].”
• Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines (2013, methodology): “For classification, we followed the pipeline used in (Sohn et al., 2011), which uses the Gaussian (convolutional) RBMs with dense SIFT as input.”
• Exemplar based Deep Discriminative and Shareable Feature Learning for scene image classification (2015, background): “Discriminative power of the filters is achieved by enforcing the features from the same category to be close, while features from different categories to be far away from each other.”
• Hierarchical Convolutional Deep Learning in Computer Vision (2013, methodology): “Additionally, this model has been applied on top of SIFT vectors to learn discriminative features for classification [121].”
• Non-Parallel Training in Voice Conversion Using an Adaptive Restricted Boltzmann Machine (2016, background): “(11), which results in softmax hidden units as [33], [34]:”