Stefano Soatto
Artificial Intelligence · 2001–2022
A researcher in the Science corpus: 65 papers; trusts 3,964 researchers and is trusted by 5,302 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,205 citations into it; #1,082 of 36,961 by trust here, #1,084 by citations
- Computer Vision and Pattern Recognition — 1,057 citations into it; #610 of 21,973 by trust here, #726 by citations
- Optimization & Training — 331 citations into it; #322 of 2,605 by trust here, #216 by citations
- Representation & Self-Supervised Learning — 273 citations into it; #370 of 3,156 by trust here, #506 by citations
- Model Architectures — 154 citations into it
- Computational Mechanics — 114 citations into it
- Evaluation & Benchmarks — 93 citations into it
- Scaling & Learning Theory — 90 citations into it; #249 of 429 by trust here, #289 by citations
Whom Stefano Soatto trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Diederik P. Kingma
- Kaiming He
- Yann LeCun
- Geoffrey E. Hinton
- Yoshua Bengio
- Ilya Sutskever
- Ross B. Girshick
- Karen Simonyan
- David G. Lowe
Who trusts Stefano Soatto overall
- Alessandro Achille
- Pratik Chaudhari
- Andrea Vedaldi
- Aditya Golatkar
- Han-Jia Ye
- Yoshua Bengio
- Daniel Cremers
- Stephan Weiss
- Radhakrishna Achanta
- Luc Van Gool
Papers from Stefano Soatto's perspective
Ordered by how strongly the researchers Stefano Soatto 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
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Entropy-SGD: biasing gradient descent into wide valleys (2016) — 882 citations
- Class segmentation and object localization with superpixel neighborhoods (2009) — 716 citations
- Discovering discriminative action parts from mid-level video representations (2012) — 249 citations
- Meta-Learning With Differentiable Convex Optimization (2019) — 1,446 citations
- Emergence of Invariance and Disentanglement in Deep Representations (2017) — 566 citations
- Dynamic Textures (2003) — 1,013 citations
- A Baseline for Few-Shot Image Classification (2019) — 646 citations
- Information Dropout: Learning Optimal Representations Through Noisy Computation (2016) — 462 citations
- Stochastic Gradient Descent Performs Variational Inference, Converges to Limit Cycles for Deep Networks (2017) — 339 citations
- Quick Shift and Kernel Methods for Mode Seeking (2008) — 998 citations
- Task2Vec: Task Embedding for Meta-Learning (2019) — 377 citations
- Dynamic texture recognition (2001) — 377 citations
- Kernel Density Estimation and Intrinsic Alignment for Shape Priors in Level Set Segmentation (2006) — 389 citations
- Stereoscopic Segmentation (2003) — 170 citations
- Integral Invariants for Shape Matching (2006) — 278 citations
- Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation (2005) — 270 citations
- Learning to Manipulate Individual Objects in an Image (2020) — 38 citations
- FDA: Fourier Domain Adaptation for Semantic Segmentation (2020) — 1,162 citations
- Toward Understanding Catastrophic Forgetting in Continual Learning (2019) — 124 citations
- Critical Learning Periods in Deep Neural Networks (2017) — 124 citations