Computer Vision, IEEE International Conference on (2011)
Nov. 6, 2011 to Nov. 13, 2011
Matthew D. Zeiler , Dept. of Computer Science, Courant Institute, New York University, USA
Graham W. Taylor , Dept. of Computer Science, Courant Institute, New York University, USA
Rob Fergus , Dept. of Computer Science, Courant Institute, New York University, USA
We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. When trained on natural images, the layers of our model capture image information in a variety of forms: low-level edges, mid-level edge junctions, high-level object parts and complete objects. To build our model we rely on a novel inference scheme that ensures each layer reconstructs the input, rather than just the output of the layer directly beneath, as is common with existing hierarchical approaches. This makes it possible to learn multiple layers of representation and we show models with 4 layers, trained on images from the Caltech-101 and 256 datasets. When combined with a standard classifier, features extracted from these models outperform SIFT, as well as representations from other feature learning methods.
R. Fergus, M. D. Zeiler and G. W. Taylor, "Adaptive deconvolutional networks for mid and high level feature learning," 2011 IEEE International Conference on Computer Vision (ICCV 2011)(ICCV), Barcelona, 2011, pp. 2018-2025.