Computer Science Masters Thesis Presentation

Wednesday, July 13, 2016 - 12:30pm to 1:30pm


4201 Newell-Simon Hall


VIVEK R. KRISHNAN, 5th Year Masters Student /VIVEK%20R.%20KRISHNAN

We consider the task of visual zero-shot learning, in which a system must learn to recognize concepts omitted from the training set. While most prior work makes use of linguistic cues to do this, we do so by using a pictorial language representation of the training set, implicitly learned by a CNN, to generalize to new classes. We first demonstrate the robustness of pictorial language classifiers (PLCs) by applying them in a weakly supervised manager: labeling unlabeled concepts for visual classes present in the training data. Specifically, we show that a PLC built on top of a CNN trained for ImageNet classification can localize humans in Graz-02 and determine the pose of birds in PASCAL-VOC without extra labeled data or additional training.  We then apply PLCs in a truly zero-shot manner, demonstrating that pictorial languages are expressive enough to detect a set of visual classes in MSCOCO that never appear in the ImageNet training set. Thesis Committee: Deva Ramanan Kayvon Fatahalian Copy of Thesis Presentation Document

For More Information, Contact:


Masters Thesis Presentation