no code implementations • 18 Nov 2019 • Heewon Kim, Seokil Hong, Bohyung Han, Heesoo Myeong, Kyoung Mu Lee
We present an elegant framework of fine-grained neural architecture search (FGNAS), which allows to employ multiple heterogeneous operations within a single layer and can even generate compositional feature maps using several different base operations.
no code implementations • ICCV 2019 • Dongmin Park, Seokil Hong, Bohyung Han, Kyoung Mu Lee
Catastrophic forgetting is a critical challenge in training deep neural networks.
1 code implementation • CVPR 2020 • Sungyong Baik, Seokil Hong, Kyoung Mu Lee
Model-agnostic meta-learning (MAML) tackles the problem by formulating prior knowledge as a common initialization across tasks, which is then used to quickly adapt to unseen tasks.