Péter Vajda

Computer Vision and Pattern Recognition · 2016–2023

A researcher in the Science corpus: 15 papers; trusts 889 researchers and is trusted by 20 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 452 citations into it; #6,649 of 21,575 by trust here, #1,929 by citations
• Artificial Intelligence — 322 citations into it; #20,254 of 35,345 by trust here, #5,359 by citations
• Efficiency & Compression — 132 citations into it; #552 of 1,264 by trust here, #187 by citations
• Model Architectures — 97 citations into it
• Representation & Self-Supervised Learning — 59 citations into it
• Optimization & Training — 50 citations into it
• Evaluation & Benchmarks — 42 citations into it
• Natural Language Processing — 21 citations into it

Whom Péter Vajda trusts overall

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

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

Who trusts Péter Vajda overall

1. Zi-Mei Yao
2. Zhen Dong

Papers from Péter Vajda's perspective

Ordered by how strongly the researchers Péter Vajda 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. ImageNet: A large-scale hierarchical image database
5. Attention is All you Need (Neural Information Processing Systems)
6. Long Short-Term Memory
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Going deeper with convolutions
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search (2018) — 1,467 citations
• Visual Transformers: Token-based Image Representation and Processing for Computer Vision (2020) — 755 citations
• ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation (2018) — 294 citations
• Unbiased Teacher for Semi-Supervised Object Detection (2021) — 634 citations
• Efficient Segmentation: Learning Downsampling Near Semantic Boundaries (2019) — 109 citations
• Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP (2022) — 767 citations
• FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions (2020) — 334 citations
• FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function (2020) — 77 citations
• Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack (2023) — 312 citations
• Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search (2018) — 313 citations
• Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation (2021) — 35 citations
• Cross-Domain Adaptive Teacher for Object Detection (2021) — 296 citations
• SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation (2020) — 449 citations
• Machine Learning at Facebook: Understanding Inference at the Edge (2019) — 490 citations
• DSD: Dense-Sparse-Dense Training for Deep Neural Networks (2016) — 219 citations