Eugene Belilovsky
Artificial Intelligence · 2015–2022
A researcher in the Science corpus: 15 papers; trusts 1,662 researchers and is trusted by 71 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 399 citations into it; #4,585 of 36,961 by trust here, #3,994 by citations
- Computer Vision and Pattern Recognition — 341 citations into it; #4,129 of 21,973 by trust here, #2,883 by citations
- Representation & Self-Supervised Learning — 104 citations into it
- Meta & Continual Learning — 86 citations into it; #128 of 1,043 by trust here, #82 by citations
- Optimization & Training — 75 citations into it; #1,120 of 2,605 by trust here, #1,989 by citations
- Model Architectures — 56 citations into it; #1,218 of 2,288 by trust here, #1,799 by citations
- Generative Models — 47 citations into it; #1,832 of 1,963 by trust here, #1,722 by citations
- Reinforcement Learning — 36 citations into it
Whom Eugene Belilovsky 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
- Karen Simonyan
- Ross B. Girshick
- Alex Graves
Who trusts Eugene Belilovsky overall
- Lucas Caccia
- Simone Scardapane
- Zeyuan Allen-Zhu
- Massimo Caccia
- Arild Nøkland
- Timothée Lesort
- Joelle Pineau
- Michele Scarpiniti
- Yigitcan Kaya
- Zheda Mai
Papers from Eugene Belilovsky's perspective
Ordered by how strongly the researchers Eugene Belilovsky 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)
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Online Continual Learning with Maximally Interfered Retrieval (2019) — 692 citations
- CLIP-Mesh: Generating textured meshes from text using pretrained image-text models (2022) — 362 citations
- A Test of Relative Similarity For Model Selection in Generative Models (2015) — 88 citations
- Scaling the Scattering Transform: Deep Hybrid Networks (2017) — 171 citations
- Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation (2020) — 60 citations
- Scattering Networks for Hybrid Representation Learning (2018) — 99 citations
- Online Learned Continual Compression with Adaptive Quantization Modules (2019) — 97 citations
- Decoupled Greedy Learning of CNNs (2019) — 140 citations
- New Insights on Reducing Abrupt Representation Change in Online Continual Learning (2021) — 295 citations
- Probing Representation Forgetting in Supervised and Unsupervised Continual Learning (2022) — 98 citations
- Reducing Representation Drift in Online Continual Learning (2021) — 21 citations
- Online Learned Continual Compression with Stacked Quantization Module (2019) — 6 citations
- Shallow Learning For Deep Networks (2018) — 5 citations
- Kymatio: Scattering Transforms in Python (2018) — 205 citations
- Greedy Layerwise Learning Can Scale to ImageNet (2018) — 219 citations