Hakan Bilen
Computer Vision and Pattern Recognition · 2014–2021
A researcher in the Science corpus: 18 papers; trusts 3,387 researchers and is trusted by 3,850 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 591 citations into it; #786 of 21,973 by trust here, #1,543 by citations
- Artificial Intelligence — 443 citations into it; #1,670 of 36,961 by trust here, #2,734 by citations
- Representation & Self-Supervised Learning — 165 citations into it; #493 of 3,156 by trust here, #473 by citations
- Model Architectures — 72 citations into it
- Optimization & Training — 70 citations into it
- Evaluation & Benchmarks — 65 citations into it
- Meta & Continual Learning — 58 citations into it; #970 of 1,043 by trust here, #880 by citations
- Generative Models — 41 citations into it
Whom Hakan Bilen trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Ross B. Girshick
- Karen Simonyan
- Yann LeCun
- Yoshua Bengio
- Ilya Sutskever
- Diederik P. Kingma
- Andrew Zisserman
Who trusts Hakan Bilen overall
- Jasper R. R. Uijlings
- Dim P. Papadopoulos
- Andrea Vedaldi
- Pichao Wang
- Krishna Kumar Singh
- Elliot Meyerson
- Andrew Zisserman
- Amir Rosenfeld
- Basura Fernando
- Vittorio Ferrari
Papers from Hakan Bilen's perspective
Ordered by how strongly the researchers Hakan Bilen 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
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Learning multiple visual domains with residual adapters (2017) — 1,069 citations
- Weakly Supervised Deep Detection Networks (2015) — 843 citations
- UvA-DARE (Digital Academic Repository) Dynamic Image Networks for Action Recognition (2016)
- Efficient Parametrization of Multi-domain Deep Neural Networks (2018) — 387 citations
- Integrated perception with recurrent multi-task neural networks (2016) — 98 citations
- Universal representations: The missing link between faces, text, planktons, and cat breeds (2017) — 154 citations
- Unsupervised Learning of Object Landmarks through Conditional Image Generation (2018) — 271 citations
- Unsupervised object learning from dense equivariant image labelling (2017) — 26 citations
- Dataset Condensation with Gradient Matching (2020) — 720 citations
- Dataset Condensation with Distribution Matching (2021) — 485 citations
- Continual Representation Learning for Biometric Identification (2020) — 50 citations
- iDLG: Improved Deep Leakage from Gradients (2020) — 844 citations
- Dataset Condensation with Differentiable Siamese Augmentation (2021) — 410 citations
- Improving Task Adaptation for Cross-domain Few-shot Learning (2021) — 14 citations
- Universal Representation Learning from Multiple Domains for Few-shot Classification (2021) — 115 citations
- Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings (2017) — 171 citations
- Weakly Supervised Object Detection with Posterior Regularization (2014) — 133 citations
- UvA-DARE (Digital Academic Repository) Self-Supervised Video Representation Learning With Odd-One-Out Networks