3 citations · 8 across the 10 of their papers we have counts for
6 papers · 1 filter
DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced Learning
Won-Seok Choi, Hyundo Lee, Dong-Sig Han +3
Recent machine learning algorithms have been developed using well-curated datasets, which often require substantial cost and resources. On the other hand, the direct use of raw dat…
L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning
Kibeom Kim, Hyundo Lee, Min Whoo Lee +3
Tasks that involve interaction with various targets are called multi-target tasks. When applying general reinforcement learning approaches for such tasks, certain targets that are…
DUEL: Adaptive Duplicate Elimination on Working Memory for Self-Supervised Learning
Won-Seok Choi, Dong-Sig Han, Hyundo Lee +2
In Self-Supervised Learning (SSL), it is known that frequent occurrences of the collision in which target data and its negative samples share the same class can decrease performanc…
Robust Imitation via Mirror Descent Inverse Reinforcement Learning
Dong-Sig Han, Hyunseo Kim, Hyundo Lee +2
Recently, adversarial imitation learning has shown a scalable reward acquisition method for inverse reinforcement learning (IRL) problems. However, estimated reward signals often b…
Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning
Taehyeong Kim, Injune Hwang, Hyundo Lee +4
Active learning is widely used to reduce labeling effort and training time by repeatedly querying only the most beneficial samples from unlabeled data. In real-world problems where…
Encoder-Powered Generative Adversarial Networks
Jiseob Kim, Seungjae Jung, Hyundo Lee +1
We present an encoder-powered generative adversarial network (EncGAN) that is able to learn both the multi-manifold structure and the abstract features of data. Unlike the conventi…