Learning Convolutional Feature Hierarchies for Visual Recognition
Koray Kavukcuoglu, Pierre Sermanet, Y-Lan Boureau et al. · 2010
We propose an unsupervised method for learning multi-stage hierarchies of sparse convolutional features. While sparse coding has become an increasingly popular method for learning visual features, it is most often trained at the patch level. Applying the resulting filters convolutionally results in highly redundant codes because overlapping patches are encoded in isolation. By training convolutionally over large image windows, our method reduces the redudancy between feature vectors at neighboring locations and improves the efficiency of the overall repre-sentation. In addition to a linear decoder that reconstructs the image from sparse features, our method trains an efficient feed-forward encoder that predicts quasi-sparse features from the input. While patch-based training rarely produces any-thing but oriented edge detectors, we show that convolutional training produces highly diverse filters, including center-surround filters, corner detectors, cross de-tectors, and oriented grating detectors. We show that using these filters in multi-stage convolutional network architecture improves performance on a number of visual recognition and detection tasks. 1
Cited by 477 works.
Authors
References
- Gradient-based learning applied to document recognition
- Histograms of Oriented Gradients for Human Detection
- Object Detection with Discriminatively Trained Part-Based Models
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- What is the best multi-stage architecture for object recognition?
- Matching pursuits with time-frequency dictionaries
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
- Efficient BackProp
- Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics