no code implementations • 4 Apr 2023 • TaeHoon Kim, Jaeyoo Park, Bohyung Han
The proposed approach has a unique perspective to utilize the previous knowledge in class incremental learning since it augments features of arbitrary target classes using examples in other classes via adversarial attacks on a previously learned classifier.
no code implementations • CVPR 2023 • Jaeyoo Park, Bohyung Han
We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy.
1 code implementation • CVPR 2022 • Minsoo Kang, Jaeyoo Park, Bohyung Han
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks.
no code implementations • ICCV 2021 • Jaeyoo Park, Minsoo Kang, Bohyung Han
We tackle catastrophic forgetting problem in the context of class-incremental learning for video recognition, which has not been explored actively despite the popularity of continual learning.
1 code implementation • 25 Mar 2022 • Jaeyoo Park, Junha Kim, Bohyung Han
We present a meta-learning framework for weakly supervised anomaly detection in videos, where the detector learns to adapt to unseen types of abnormal activities effectively when only video-level annotations of binary labels are available.
no code implementations • NeurIPS 2020 • Seohyun Kim, Jaeyoo Park, Bohyung Han
We propose a local-to-global representation learning algorithm for 3D point cloud data, which is appropriate to handle various geometric transformations, especially rotation, without explicit data augmentation with respect to the transformations.