Timezone: »

Learning Convolutional Feature Hierarchies for Visual Recognition
koray kavukcuoglu · Pierre Sermanet · Y-Lan Boureau · Karol Gregor · Michael Mathieu · Yann LeCun

Tue Dec 07 11:20 AM -- 11:25 AM (PST) @ Regency Ballroom

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 representation. 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 anything but oriented edge detectors, we
show that convolutional training produces highly diverse filters,
including center-surround filters, corner detectors, cross
detectors, 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.

Author Information

koray kavukcuoglu (DeepMind)
Pierre Sermanet (New York University)
Y-Lan Boureau (Facebook)
Karol Gregor (Google DeepMind)
Michael Mathieu
Yann LeCun (Facebook)

Yann LeCun is VP & Chief AI Scientist at Meta and Silver Professor at NYU affiliated with the Courant Institute of Mathematical Sciences & the Center for Data Science. He was the founding Director of FAIR (Meta's AI Research group) and of the NYU Center for Data Science. He received an Engineering Diploma from ESIEE (Paris) and a PhD from Sorbonne Université. After a postdoc in Toronto he joined AT&T Bell Labs in 1988, and AT&T Labs in 1996 as Head of Image Processing Research. He joined NYU as a professor in 2003 and Facebook in 2013. His interests include AI machine learning, computer perception, robotics and computational neuroscience. He is the recipient of the 2018 ACM Turing Award (with Geoffrey Hinton and Yoshua Bengio) for "conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing", a member of the National Academy of Sciences, the National Academy of Engineering and a Chevalier de la Légion d’Honneur.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors