Events Calendar

AI Seminar

Speaker: Fei Sha, UCLA

Talk Title: Large-scale Zero-Shot Learning

Abstract: Abstract: Is it possible for computer vision systems to recognize visual object categories that they have never seen before? More precisely, in the paradigm of zero-shot learning, a learner has access to only a subset of the labels in the labeling space (and its associated exemplar images). Nonetheless, our goal for the learner is to recognize future occurrences of images from all possible categories. This is an important research problem with great application potential for automatic object recognition in the wild where the number of possible visual categories continuously rises and there is little hope to collect adequate labeling samples for those categories fast enough.

In this talk, I will describe a few work from my research group on tackling this challenge. We have demonstrated that it is possible to train vision systems on the ImageNet images from 1,000 visual categories yet attaining meaningful results on recognizing a disjoint set of 20,000 visual categories.

This is a joint research work with my PhD students (Soravit Changpinyo and Weilun Chao ) at USC and our collaborator Prof. Boqing Gong (U. of Central Florida).

Host: Emilio Ferrara

Location: Information Science Institute (ISI) - 11th floor Large Conference room

Audiences: Everyone Is Invited

Contact: Kary LAU