Timezone: »

Meta Variance Transfer: Learning to Augment from the Others
Seong-Jin Park · Seungju Han · Ji-won Baek · Insoo Kim · Juhwan Song · Hae Beom Lee · Jae-Joon Han · Sung Ju Hwang

Thu Jul 16 06:00 AM -- 06:45 AM & Thu Jul 16 06:00 PM -- 06:45 PM (PDT) @

Humans have the ability to robustly recognize objects with various factors of variations such as nonrigid transformations, background noises, and changes in lighting conditions. However, training deep learning models generally require huge amount of data instances under diverse variations, to ensure its robustness. To alleviate the need of collecting large amount of data and better learn to generalize with scarce data instances, we propose a novel meta-learning method which learns to transfer factors of variations from one class to another, such that it can improve the classification performance on unseen examples. Transferred variations generate virtual samples that augment the feature space of the target class during training, simulating upcoming query samples with similar variations. By sharing the factors of variations across different classes, the model becomes more robust to variations in the unseen examples and tasks using small number of examples per class. We validate our model on multiple benchmark datasets for few-shot classification and face recognition, on which our model significantly improves the performance of the base model, outperforming relevant baselines.

Author Information

Seong-Jin Park (Samsung Advanced Institute of Technology)
Seungju Han (Samsung Advanced Institute of Technology)
Ji-won Baek (Samsung Advanced Institute of Technology)
Insoo Kim (Samsung Advanced Institute of Technology)
Juhwan Song (Samsung Advanced Institute of Technology)
Hae Beom Lee (KAIST)
Jae-Joon Han (Samsung Advanced Institute of Technology)
Sung Ju Hwang (KAIST, AITRICS)

More from the Same Authors