Michal Drozdzal

Computer Vision and Pattern Recognition · 2016–2021

A researcher in the Science corpus: 14 papers; trusts 1,329 researchers and is trusted by 15 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 395 citations into it; #7,366 of 21,575 by trust here, #3,017 by citations
• Artificial Intelligence — 252 citations into it; #33,604 of 35,345 by trust here, #6,848 by citations
• Generative Models — 114 citations into it
• Model Architectures — 92 citations into it; #2,144 of 2,278 by trust here, #1,191 by citations
• Evaluation & Benchmarks — 70 citations into it
• Optimization & Training — 48 citations into it
• Media Technology — 33 citations into it
• Representation & Self-Supervised Learning — 30 citations into it

Whom Michal Drozdzal trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Kaiming He
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Diederik P. Kingma
5. Yoshua Bengio
6. Karen Simonyan
7. Ross B. Girshick
8. Christian Szegedy
9. Ilya Sutskever
10. Yann LeCun

Who trusts Michal Drozdzal overall

1. Fabian Isensee
2. Luis Villaseñor Pineda
3. Arantxa Casanova
4. Alex Kendall
5. Adriana Romero
6. Amaia Salvador
7. Md. Zahangir Alom
8. Haonan Wang
9. Weihao Weng
10. Junjie Hu

Papers from Michal Drozdzal's perspective

Ordered by how strongly the researchers Michal Drozdzal trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation (2016) — 1,668 citations
• Instance Selection for GANs (2020) — 41 citations
• Instance-Conditioned GAN (2021) — 164 citations
• The Liver Tumor Segmentation Benchmark (LiTS) (2019) — 1,500 citations
• Parameter Prediction for Unseen Deep Architectures (2021) — 109 citations
• Learnable Explicit Density for Continuous Latent Space and Variational Inference (2017) — 28 citations
• The Importance of Skip Connections in Biomedical Image Segmentation (2016) — 1,139 citations
• Inverse Cooking: Recipe Generation From Food Images (2018) — 170 citations
• On the Evaluation of Conditional GANs (2019) — 51 citations
• Elucidating image-to-set prediction: An analysis of models, losses and datasets (2019) — 15 citations
• fastMRI: An Open Dataset and Benchmarks for Accelerated MRI (2018) — 1,072 citations
• On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation (2018) — 26 citations
• Deep Learning: A Primer for Radiologists. (2017) — 1,015 citations
• A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images (2016) — 921 citations