University of Cambridge > Talks.cam > Microsoft Research Machine Learning and Perception Seminars > Closing the gap between weakly and fully supervised methods

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Closing the gap between weakly and fully supervised methods

Download to your calendar using vCal

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins .

This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending

Learning visual classes is traditionally done in a fully supervised setting, where the location of training instances are manually annotated by bounding-boxes or pixelwise segmentations. After learning a model of a class from this data, it can be used to recognise and localise novel instances in test images. On the other hand, weakly supervised techniques try to learn such models from training images labeled only by the presence or absence of the class, without location annotation. While these techniques can substantially reduce the manual effort necessary to learn a class, fully supervised methods typically deliver models that perform considerably better on test data. In this talk I will present recent advances towards closing this performance gap for the two tasks of action recognition and semantic segmentation. These are steps towards the goal of devising weakly supervised techniques that deliver models of the same quality as fully supervised ones.

This talk is part of the Microsoft Research Machine Learning and Perception Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

zoom-- Contact organiser for the link Room 1.02, Faculty of Classics Craik Seminar Room, Craik-Marshall Building, Downing Site

Other talks

Machine Politics? Computers and AI in the History of Political Thought Title to be confirmed Online Causal Inference Seminar Complete and Submit Project Choice Forms Rothschild Public Lecture | Forty years of causal inference: Report of a great-grandfather Differences between Robin and Neumann eigenvalues
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity