-
Upload Video
videos in mp4/mov/flv
close
Upload video
Note: publisher must agree to add uploaded document -
Upload Slides
slides or other attachment
close
Upload Slides
Note: publisher must agree to add uploaded document -
Feedback
help us improve
close
Feedback
Please help us improve your experience by sending us a comment, question or concern
Please help transcribe this video using our simple transcription tool. You need to be logged in to do so.
Description
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. Features extracted from these
models, in combination with a standard classi?er, outperform SIFT and
representations from other feature learning approaches. Joint work
with Matt Zeiler (NYU) and Graham Taylor (NYU).