Timezone: »

XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning
Sung Whan Yoon · Do-Yeon Kim · Jun Seo · Jaekyun Moon

Wed Jul 15 03:00 PM -- 03:45 PM & Thu Jul 16 02:00 AM -- 02:45 AM (PDT) @

Learning novel concepts while preserving prior knowledge is a long-standing challenge in machine learning. The challenge gets greater when a novel task is given with only a few labeled examples, a problem known as incremental few-shot learning. We propose XtarNet, which learns to extract task-adaptive representation (TAR) for facilitating incremental few-shot learning. The method utilizes a backbone network pretrained on a set of base categories while also employing additional modules that are meta-trained across episodes. Given a new task, the novel feature extracted from the meta-trained modules is mixed with the base feature obtained from the pretrained model. The process of combining two different features provides TAR and is also controlled by meta-trained modules. The TAR contains effective information for classifying both novel and base categories. The base and novel classifiers quickly adapt to a given task by utilizing the TAR. Experiments on standard image datasets indicate that XtarNet achieves state-of-the-art incremental few-shot learning performance. The concept of TAR can also be used in conjunction with existing incremental few-shot learning methods; extensive simulation results in fact show that applying TAR enhances the known methods significantly.

Author Information

Sung Whan Yoon (Ulsan National Institute of Science and Technology (UNIST))
Do-Yeon Kim (Korea Advanced Institute of Science and Technology)
Jun Seo (Korea Advanced Institute of Science and Technology(KAIST))
Jaekyun Moon (KAIST)

More from the Same Authors