Sung Ju Hwang
Artificial Intelligence · with Lee · 2011–2022
A researcher in the Science corpus: 31 papers; trusts 3,218 researchers and is trusted by 546 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 855 citations into it; #2,792 of 36,961 by trust here, #1,735 by citations
- Computer Vision and Pattern Recognition — 645 citations into it; #2,419 of 21,973 by trust here, #1,560 by citations
- Representation & Self-Supervised Learning — 260 citations into it; #476 of 3,156 by trust here, #353 by citations
- Optimization & Training — 138 citations into it; #1,649 of 2,605 by trust here, #2,084 by citations
- Meta & Continual Learning — 134 citations into it; #243 of 1,043 by trust here, #176 by citations
- Model Architectures — 101 citations into it
- Reinforcement Learning — 100 citations into it
- Efficiency & Compression — 62 citations into it
Whom Sung Ju Hwang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Yoshua Bengio
- Yann LeCun
- Diederik P. Kingma
- Ilya Sutskever
- David G. Lowe
- Jia Deng
- Ross B. Girshick
Who trusts Sung Ju Hwang overall
- Micah Hodosh
- Jaehong Yoon
- Sangwon Jung
- Yu Zhang
- Peter Young
- Jianping Gou
- Clint Solomon Mathialagan
- Yunchao Gong
- Zeynep Akata
- Yanwei Fu
Papers from Sung Ju Hwang's perspective
Ordered by how strongly the researchers Sung Ju Hwang trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Lifelong Learning with Dynamically Expandable Networks (2017) — 1,463 citations
- Sharing features between objects and their attributes (2011) — 125 citations
- Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search (2012) — 130 citations
- Learning to Propagate Labels: Transductive Propagation Network for Few-Shot Learning (2018) — 758 citations
- Expanding object detector's Horizon: Incremental learning framework for object detection in videos (2015) — 49 citations
- Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss (2018) — 430 citations
- Asymmetric multi-task learning based on task relatedness and loss (2016) — 109 citations
- MPViT: Multi-Path Vision Transformer for Dense Prediction (2021) — 361 citations
- Online Coreset Selection for Rehearsal-based Continual Learning (2021) — 187 citations
- Learning What and Where to Transfer (2019) — 165 citations
- Skill-based Meta-Reinforcement Learning (2022) — 57 citations
- Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations (2022) — 357 citations
- On the Soft-Subnetwork for Few-shot Class Incremental Learning (2022) — 65 citations
- Forget-free Continual Learning with Winning Subnetworks (2022) — 173 citations
- Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models (2022) — 64 citations
- Model-augmented Prioritized Experience Replay (2022) — 22 citations
- Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation (2021) — 227 citations
- Rethinking the Representational Continuity: Towards Unsupervised Continual Learning (2021) — 18 citations
- Representational Continuity for Unsupervised Continual Learning (2021) — 152 citations
- Federated Continual Learning with Weighted Inter-client Transfer (2020) — 322 citations