no code implementations • 9 Nov 2023 • Jaehyeon Son, Soochan Lee, Gunhee Kim
Over the past decade, deep neural networks have demonstrated significant success using the training scheme that involves mini-batch stochastic gradient descent on extensive datasets.
1 code implementation • NeurIPS 2023 • Soochan Lee, Jaehyeon Son, Gunhee Kim
That is, we propose to formulate continual learning as a sequence modeling problem, allowing advanced sequence models to be utilized for continual learning.
1 code implementation • 12 Jun 2023 • Soochan Lee, Gunhee Kim
Generating intermediate steps, or Chain of Thought (CoT), is an effective way to significantly improve language models' (LM) multi-step reasoning capability.
1 code implementation • ICLR 2020 • Soochan Lee, Junsoo Ha, Dongsu Zhang, Gunhee Kim
Despite the growing interest in continual learning, most of its contemporary works have been studied in a rather restricted setting where tasks are clearly distinguishable, and task boundaries are known during training.
no code implementations • ICLR 2019 • Soochan Lee, Junsoo Ha, Gunhee Kim
Recent advances in conditional image generation tasks, such as image-to-image translation and image inpainting, are largely accounted to the success of conditional GAN models, which are often optimized by the joint use of the GAN loss with the reconstruction loss.
no code implementations • CVPR 2018 • Junhyug Noh, Soochan Lee, Beomsu Kim, Gunhee Kim
We propose methods of addressing two critical issues of pedestrian detection: (i) occlusion of target objects as false negative failure, and (ii) confusion with hard negative examples like vertical structures as false positive failure.