Research Projects

Multi-View Learning in the Presence of View Disagreement

Trevor Darrell, C. Mario Christhoudias¹ and Raquel Urtasun²

Defense Advanced Research Projects Agency

Traditional multi-view learning approaches suffer in the presence of view disagreement, i.e., when samples in each view do not belong to the same class due to view corruption, occlusion or other noise processes. In this paper we present a multi-view learning approach that uses a conditional entropy criterion to detect view disagreement. Once detected, samples with view disagreement are filtered and standard multi-view learning methods can be successfully applied to the remaining samples. Experimental evaluation on synthetic and audio-visual databases demonstrates that the detection and filtering of view disagreement considerably increases the performance of traditional multi-view learning approaches.

[1]

Mario Christoudias, Raquel Urtasun and Trevor Darrell, Multi-View Learning in the Presence of View Disagreement, UAI 2008

¹MIT; ICSI
²ICSI