Timezone: »

Controlled Recognition Bounds for Visual Learning and Exploration
Vasiliy Karasev · Chiuso Alessandro c/o Dip. I Informazione · Stefano Soatto

Mon Dec 03 07:00 PM -- 12:00 AM (PST) @ Harrah’s Special Events Center 2nd Floor

We describe the tradeoff between the performance in a visual recognition problem and the control authority that the agent can exercise on the sensing process. We focus on the problem of “visual search” of an object in an otherwise known and static scene, propose a measure of control authority, and relate it to the expected risk and its proxy (conditional entropy of the posterior density). We show this analytically, as well as empirically by simulation using the simplest known model that captures the phenomenology of image formation, including scaling and occlusions. We show that a “passive” agent given a training set can provide no guarantees on performance beyond what is afforded by the priors, and that an “omnipotent” agent, capable of infinite control authority, can achieve arbitrarily good performance (asymptotically).

Author Information

Vasiliy Karasev (UCLA)
Chiuso Alessandro c/o Dip. I Informazione (University of Padova)
Stefano Soatto (UCLA)

More from the Same Authors