156 citations · 395 across the 20 of their papers we have counts for
20 papers
Effortless Integration of Memory Management into Open-Domain Conversation Systems
Eunbi Choi, Kyoung-Woon On, Gunsoo Han +6
Open-domain conversation systems integrate multiple conversation skills into a single system through a modular approach. One of the limitations of the system, however, is the absen…
MAGVLT: Masked Generative Vision-and-Language Transformer
Sungwoong Kim, Daejin Jo, Donghoon Lee +1
While generative modeling on multimodal image-text data has been actively developed with large-scale paired datasets, there have been limited attempts to generate both image and te…
LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward
Daejin Jo, Sungwoong Kim, Daniel Wontae Nam +4
Episodic count has been widely used to design a simple yet effective intrinsic motivation for reinforcement learning with a sparse reward. However, the use of episodic count in a h…
Selective Token Generation for Few-shot Natural Language Generation
Daejin Jo, Taehwan Kwon, Eun-Sol Kim +1
Natural language modeling with limited training data is a challenging problem, and many algorithms make use of large-scale pretrained language models (PLMs) for this due to its gre…
Insights From the NeurIPS 2021 NetHack Challenge
Eric Hambro, Sharada Mohanty, Dmitrii Babaev +26
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' i…
Contrastive Regularization for Semi-Supervised Learning
Doyup Lee, Sungwoong Kim, Ildoo Kim +3
Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high pe…
Automated Learning Rate Scheduler for Large-batch Training
Chiheon Kim, Saehoon Kim, Jongmin Kim +2
Large-batch training has been essential in leveraging large-scale datasets and models in deep learning. While it is computationally beneficial to use large batch sizes, it often re…
Hybrid Generative-Contrastive Representation Learning
Saehoon Kim, Sungwoong Kim, Juho Lee
Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There ar…
Spatially Consistent Representation Learning
Byungseok Roh, Wuhyun Shin, Ildoo Kim +1
Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive p…
Learning Loss for Test-Time Augmentation
Ildoo Kim, Younghoon Kim, Sungwoong Kim
Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the…
Visual Concept Reasoning Networks
Taesup Kim, Sungwoong Kim, Yoshua Bengio
A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connec…
AutoCLINT: The Winning Method in AutoCV Challenge 2019
Woonhyuk Baek, Ildoo Kim, Sungwoong Kim +1
NeurIPS 2019 AutoDL challenge is a series of six automated machine learning competitions. Particularly, AutoCV challenges mainly focused on classification tasks on visual domain. I…
torchgpipe: On-the-fly Pipeline Parallelism for Training Giant Models
Chiheon Kim, Heungsub Lee, Myungryong Jeong +5
We design and implement a ready-to-use library in PyTorch for performing micro-batch pipeline parallelism with checkpointing proposed by GPipe (Huang et al., 2019). In particular,…
Spatially Attentive Output Layer for Image Classification
Ildoo Kim, Woonhyuk Baek, Sungwoong Kim
Most convolutional neural networks (CNNs) for image classification use a global average pooling (GAP) followed by a fully-connected (FC) layer for output logits. However, this spat…
Mining GOLD Samples for Conditional GANs
Sangwoo Mo, Chiheon Kim, Sungwoong Kim +2
Conditional generative adversarial networks (cGANs) have gained a considerable attention in recent years due to its class-wise controllability and superior quality for complex gene…
Scalable Neural Architecture Search for 3D Medical Image Segmentation
Sungwoong Kim, Ildoo Kim, Sungbin Lim +5
In this paper, a neural architecture search (NAS) framework is proposed for 3D medical image segmentation, to automatically optimize a neural architecture from a large design space…
Fast AutoAugment
Sungbin Lim, Ildoo Kim, Taesup Kim +2
Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically s…
Edge-labeling Graph Neural Network for Few-shot Learning
Jongmin Kim, Taesup Kim, Sungwoong Kim +1
In this paper, we propose a novel edge-labeling graph neural network (EGNN), which adapts a deep neural network on the edge-labeling graph, for few-shot learning. The previous grap…
Bayesian Model-Agnostic Meta-Learning
Taesup Kim, Jaesik Yoon, Ousmane Dia +3
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper,…
A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
Jörg H. Kappes, Bjoern Andres, Fred A. Hamprecht +10
Szeliski et al. published an influential study in 2006 on energy minimization methods for Markov Random Fields (MRF). This study provided valuable insights in choosing the best opt…