Timezone: »

Learning Classifiers for Target Domain with Limited or No Labels
Pengkai Zhu · Hanxiao Wang · Venkatesh Saligrama

Wed Jun 12 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #133

In computer vision applications, such as domain adaptation (DA), few shot learning (FSL) and zero-shot learning (ZSL), we encounter new objects and environments, for which insufficient examples exist to allow for training “models from scratch,” and methods that adapt existing models, trained on the presented training environment, to the new scenario are required. We propose a novel visual attribute encoding method that encodes each image as a low-dimensional probability vector composed of prototypical part-type probabilities. The prototypes are learnt to be representative of all training data. At test-time we utilize this encoding as an input to a classifier. At test-time we freeze the encoder and only learn/adapt the classifier component to limited annotated labels in FSL; new semantic attributes in ZSL. We conduct extensive experiments on benchmark datasets. Our method outperforms state-of-art methods trained for the specific contexts (ZSL, FSL, DA).

Author Information

Pengkai Zhu (Boston University)
Hanxiao Wang (Boston University)
Venkatesh Saligrama (Boston University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors