- Full text PDF available (5)
- This year (0)
- Last five years (5)
Traditional active learning allows a (machine) learner to query the (human) teacher for labels on examples it finds confusing. The teacher then provides a label for only that instance. This is quite restrictive. In this paper, we propose a learning paradigm in which the learner communicates its belief (i.e. predicted label) about the actively chosen example… (More)
We propose to model relative attributes 1 that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can capture that animal A is 'furrier' than animal B, or image X is 'brighter' than image B. Given training data stating how object/scene categories relate according to different… (More)
Computer Vision algorithms make mistakes. In human-centric applications, some mistakes are more annoying to users than others. In order to design algorithms that minimize the annoyance to users, we need access to an annoyance or cost matrix that holds the annoyance of each type of mistake. Such matrices are not readily available, especially for a wide gamut… (More)
Implemented and researched algorithms in the object detection group, under the mentorship of Dr. Sud-heendra Vijayanarasimhan. Investigated face recognition techniques for a ten-week independent research project under the mentor-ship of Professor Margaret Martonosi and her graduate students.