Sylvain Gelly
Artificial Intelligence · with Lucic · 2006–2021
A researcher in the Science corpus: 41 papers; trusts 2,794 researchers and is trusted by 6,517 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 996 citations into it; #630 of 36,961 by trust here, #267 by citations
- Computer Vision and Pattern Recognition — 963 citations into it; #532 of 21,973 by trust here, #166 by citations
- Representation & Self-Supervised Learning — 372 citations into it; #990 of 3,156 by trust here, #251 by citations
- Generative Models — 358 citations into it; #158 of 1,963 by trust here, #159 by citations
- Optimization & Training — 172 citations into it
- Evaluation & Benchmarks — 167 citations into it; #937 of 3,155 by trust here, #558 by citations
- Reinforcement Learning — 144 citations into it; #456 of 2,250 by trust here, #807 by citations
- Model Architectures — 95 citations into it; #653 of 2,288 by trust here, #80 by citations
Whom Sylvain Gelly trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Kaiming He
- Rémi Coulom
- Richard S. Sutton
- Yann LeCun
- Jimmy Ba
- Ilya Sutskever
Who trusts Sylvain Gelly overall
- David Silver
- Yuxi Li
- Christopher D. Rosin
- R´emi Munos
- Ali Borji
- Yoshua Bengio
- Sergey Levine
- Nathan R Sturtevant
- Ole-Christoffer Granmo
- Richard S. Sutton
Papers from Sylvain Gelly's perspective
Ordered by how strongly the researchers Sylvain Gelly 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- 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
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (2020) — 66,490 citations
- Big Transfer (BiT): General Visual Representation Learning (2019) — 1,392 citations
- Parameter-Efficient Transfer Learning for NLP (2019) — 6,877 citations
- Are GANs Created Equal? A Large-Scale Study (2017) — 1,114 citations
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations (2018) — 1,814 citations
- Assessing Generative Models via Precision and Recall (2018) — 758 citations
- Towards Accurate Generative Models of Video: A New Metric & Challenges (2018) — 1,343 citations
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark (2019) — 558 citations
- Wasserstein Auto-Encoders (2017) — 1,174 citations
- On Mutual Information Maximization for Representation Learning (2019) — 567 citations
- On Self Modulation for Generative Adversarial Networks (2018) — 111 citations
- Episodic Curiosity through Reachability (2018) — 291 citations
- Large Scale Learning of General Visual Representations for Transfer (2019) — 104 citations
- High-Fidelity Image Generation With Fewer Labels (2019) — 175 citations
- Self-Supervised Learning of Video-Induced Visual Invariances (2019) — 67 citations
- On Robustness and Transferability of Convolutional Neural Networks (2020) — 174 citations
- The GAN Landscape: Losses, Architectures, Regularization, and Normalization (2018) — 159 citations
- Investigating object compositionality in Generative Adversarial Networks (2018) — 49 citations
- The grand challenge of computer Go (2012) — 240 citations
- AdaGAN: Boosting Generative Models (2017) — 232 citations