Search Results for author: Soochan Lee

Found 6 papers, 3 papers with code

When Meta-Learning Meets Online and Continual Learning: A Survey

no code implementations9 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.

Continual Learning Meta-Learning

Recasting Continual Learning as Sequence Modeling

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.

Continual Learning

Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models

1 code implementation12 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.

A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning

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.

Continual Learning Image Classification +1

Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation

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.

Conditional Image Generation Image Inpainting +3

Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors

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.

Occlusion Handling Pedestrian Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.