BEGIN:VCALENDAR
METHOD:PUBLISH
VERSION:2.0
PRODID:-//Cornell U. Department of Computer Science//Brown Bag Seminar//EN
BEGIN:VEVENT
SUMMARY:Brown bag: Bharath Hariharan
DESCRIPTION:Title: Deep Learning on a Diet: Reducing the Supervision
	 Required for Visual Recognition\nSpeaker: Bharath Hariharan\nAbstract:
	 Over the past half-decade\, computer vision researchers have found an
	 extremely effective way of building visual recognition systems:
	 pre-train a convolutional network on a massive labeled dataset such as
	 ImageNet\, and then fine-tune this convolutional network on the visual
	 recognition task of interest using another massive labeled dataset. Both
	 stages of this two-step pipeline require hundreds of thousands\, if not
	 millions\, of labeled images.\n\nThis effectively puts visual
	 recognition out of the reach of anyone except Google\, Facebook and
	 their ilk. It also is in stark contrast to the ability of humans to
	 build their vision systems with essentially no labels at all.\n\nHow can
	 we get computers to be as label-efficient as humans? How can we get
	 computers to build visual representations from unlabeled data? How can
	 we get computers to generalize to new tasks or visual concepts without
	 annotations? This talk will provide some answers to these questions\,
	 and some directions for future research.
LOCATION:Gates 122
UID:2017-09-19
STATUS:CONFIRMED
DTSTART:20170919T160000Z
DTEND:20170919T170000Z
LAST-MODIFIED:20170914T202139Z
ORGANIZER;CN=Jonathan Shi:http://www.cs.cornell.edu/~jshi/brownbag/
DTSTAMP:20260408T165601Z
END:VEVENT
END:VCALENDAR