Sciweavers

Share
ICCV
2011
IEEE

Adaptive Deconvolutional Networks for Mid and High Level Feature Learning

7 years 10 months ago
Adaptive Deconvolutional Networks for Mid and High Level Feature Learning
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.
Matthew D. Zeiler, Graham W. Taylor, Rob Fergus
Added 11 Dec 2011
Updated 11 Dec 2011
Type Journal
Year 2011
Where ICCV
Authors Matthew D. Zeiler, Graham W. Taylor, Rob Fergus
Comments (0)
books