Kihyuk Sohn
Computer Vision and Pattern Recognition · 2011–2023
A researcher in the Science corpus: 29 papers; trusts 3,283 researchers and is trusted by 7,597 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 929 citations into it; #423 of 21,973 by trust here, #757 by citations
- Artificial Intelligence — 686 citations into it; #638 of 36,961 by trust here, #1,310 by citations
- Representation & Self-Supervised Learning — 291 citations into it; #87 of 3,156 by trust here, #262 by citations
- Generative Models — 198 citations into it; #187 of 1,963 by trust here, #269 by citations
- Optimization & Training — 114 citations into it
- Model Architectures — 94 citations into it; #1,012 of 2,288 by trust here, #1,290 by citations
- Evaluation & Benchmarks — 92 citations into it
- Signal Processing — 88 citations into it; #728 of 7,592 by trust here, #1,353 by citations
Whom Kihyuk Sohn trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Diederik P. Kingma
- Kaiming He
- Yann LeCun
- Ross B. Girshick
- Ilya Sutskever
- David G. Lowe
- Ruslan Salakhutdinov
Who trusts Kihyuk Sohn overall
- Yoshua Bengio
- Kristen Grauman
- Dinesh Jayaraman
- Honglak Lee
- Trevor Darrell
- Luc Van Gool
- Andrea Vedaldi
- Sercan Ö. Arik
- Dacheng Tao
- Jianwei Yang
Papers from Kihyuk Sohn's perspective
Ordered by how strongly the researchers Kihyuk Sohn trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- 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
- Going deeper with convolutions
Their papers
- Improved Deep Metric Learning with Multi-class N-pair Loss Objective (2016) — 2,481 citations
- Attribute2Image: Conditional Image Generation from Visual Attributes (2015) — 808 citations
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (2020) — 4,872 citations
- Learning to Disentangle Factors of Variation with Manifold Interaction (2014) — 254 citations
- Learning to Adapt Structured Output Space for Semantic Segmentation (2018) — 1,735 citations
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring (2019) — 796 citations
- Learning Invariant Representations with Local Transformations (2012) — 196 citations
- Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling (2013) — 194 citations
- Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units (2016) — 530 citations
- ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring (2020) — 479 citations
- A Simple Semi-Supervised Learning Framework for Object Detection (2020) — 598 citations
- Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction (2015) — 221 citations
- MAGVIT: Masked Generative Video Transformer (2022) — 394 citations
- Feature Transfer Learning for Face Recognition With Under-Represented Data (2019) — 326 citations
- Towards Large-Pose Face Frontalization in the Wild (2017) — 334 citations
- Efficient learning of sparse, distributed, convolutional feature representations for object recognition (2011) — 135 citations
- Domain Adaptation for Structured Output via Discriminative Patch Representations (2019) — 334 citations
- CutPaste: Self-Supervised Learning for Anomaly Detection and Localization (2021) — 1,213 citations
- Photorealistic Video Generation with Diffusion Models (2023) — 341 citations
- Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation (2023) — 665 citations