Skip to content

Instantly share code, notes, and snippets.

@sergicastellasape

sergicastellasape/top-cited-2020-papers.tsv

Last active February 29, 2024 08:53
Show Gist options
  • Save sergicastellasape/7df5f0df47fa04e630bd7f17eeb49d28 to your computer and use it in GitHub Desktop.
Save sergicastellasape/7df5f0df47fa04e630bd7f17eeb49d28 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
top-cited-2020-papers.tsv
Title Tweets Citations Organization Country Org Type
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 142 12042 Google USA industry
A Simple Framework for Contrastive Learning of Visual Representations 16 8476 Google USA industry
Language Models are Few-Shot Learners 331 7903 OpenAI USA industry
YOLOv4: Optimal Speed and Accuracy of Object Detection 20 7860 Academia Sinica Taiwan industry
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. 53 6362 Google USA industry
Momentum Contrast for Unsupervised Visual Representation Learning 8 6060 Meta USA industry
End-to-End Object Detection with Transformers 43 4998 Meta, Paris Dauphine University France, USA industry
Analyzing and Improving the Image Quality of StyleGAN 44 3101 Aalto University, NVIDIA Finland, USA industry
EfficientDet: Scalable and Efficient Object Detection 7 3081 Google USA industry
Advances and Open Problems in Federated Learning 5 2921 Australian National University, Carnegie Mellon University, Cornell University, Emory University, École Polytechnique Fédérale de Lausanne, Georgia Institute of Technology, Google, Hong Kong University of Science and Technology, INRIA, IT University of Copenhagen, MIT, Nanyang Technological University, Princeton University, Rutgers University, Stanford University, UC Berkeley, UC San Diego, University of Illinois Urbana-Champaign, University of Oulu, University of Pittsburgh, University of Southern California, University of Virginia, University of Warwick, University of Washington, University of Wisconsin-Madison Australia, China, Denmark, Finland, France, Singapore, Switzerland, UK, USA industry
Unsupervised Cross-lingual Representation Learning at Scale 6 2857 Meta USA industry
Bootstrap your own latent: A new approach to self-supervised Learning 13 2827 DeepMind, Imperial College London UK industry
Training data-efficient image transformers & distillation through attention 45 2558 Meta, Sorbonne University France, USA industry
Random Erasing Data Augmentation. 2 2453 University of Technology Sydney, Xiamen University Australia, China academia
nuScenes: A Multimodal Dataset for Autonomous Driving 3 2366 nuTonomy USA industry
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis 188 2283 Google, UC Berkeley, UC San Diego USA academia
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators 2142 CIFAR, Google, Stanford University Canada, USA academia
Improved protein structure prediction using potentials from deep learning 2121 DeepMind, Francis Crick Institute, University College London UK industry
Transformers: State-of-the-Art Natural Language Processing 2071 Hugging Face USA industry
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments 12 1847 INRIA, Meta France, USA industry
Supervised Contrastive Learning 29 1835 Boston University, Google, MIT, Snap Inc. USA industry
Improved Baselines with Momentum Contrastive Learning 1 1782 Meta USA industry
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations 34 1777 Meta USA industry
Exploring Simple Siamese Representation Learning 73 1767 Meta USA industry
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks 5 1713 Dalian University of Technology, Harbin Institute of Technology, Tianjin University China academia
RandAugment: Practical Automated Data Augmentation with a Reduced Search Space 3 1684 Google USA industry
Self-Training With Noisy Student Improves ImageNet Classification 19 1674 Carnegie Mellon University, Google USA industry
Longformer: The Long-Document Transformer 55 1650 Allen Institute for Artificial Intelligence USA industry
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence 1603 Google USA industry
Face2Face: Real-time Face Capture and Reenactment of RGB Videos 1 1532 Max Planck Institute for Informatics, Stanford University, University of Erlangen-Nuremberg Germany, USA academia
Image Segmentation Using Deep Learning: A Survey 13 1450 Qualcomm, Snapchat, UC Los Angeles, University of Extremadura, University of Texas at Dallas, University of Waterloo Canada, Spain, USA academia
Unsupervised Data Augmentation for Consistency Training 11 1345 Carnegie Mellon University, Google USA industry
Big Self-Supervised Models are Strong Semi-Supervised Learners 16 1314 Google USA industry
SpanBERT: Improving Pre-training by Representing and Predicting Spans 2 1307 Allen Institute for Artificial Intelligence, Meta, Princeton University, University of Washington USA industry
Conformer: Convolution-augmented Transformer for Speech Recognition 51 1214 Google USA industry
Scalability in Perception for Autonomous Driving: Waymo Open Dataset 1209 Google, Waymo USA industry
Denoising Diffusion Probabilistic Models 108 1206 UC Berkeley USA academia
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks 10 1150 Allen Institute for Artificial Intelligence, University of Washington USA academia, industry
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation 1141 Hefei University of Technology, Kuaishou Technology, National University of Singapore, University of Science and Technology of China China, Singapore academia
Open Graph Benchmark: Datasets for Machine Learning on Graphs 22 1112 Harvard University, Microsoft, Stanford University, Technical University Dortmund Germany, USA academia
Dense Passage Retrieval for Open-Domain Question Answering 23 1106 Meta, Princeton University, University of Washington USA industry
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning 1 1052 École Polytechnique Fédérale de Lausanne, Google, New York University Switzerland, USA industry
Data-Efficient Image Recognition with Contrastive Predictive Coding 1031 DeepMind, UC Berkeley UK, USA industry
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages 1016 Stanford University USA academia
ResNeSt: Split-Attention Networks 5 994 Amazon, ByteDance, Meta, SenseTime, Snap Inc., UC Davis China, USA industry
Self-Supervised Learning of Pretext-Invariant Representations 2 993 Meta USA industry
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks 2 971 Microsoft, University of Washington USA industry
Implicit Neural Representations with Periodic Activation Functions 38 963 Stanford University USA academia
TinyBERT: Distilling BERT for Natural Language Understanding 954 Huawei, Huazhong University of Science and Technology China industry
Big Bird: Transformers for Longer Sequences 10 929 Google USA industry
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning 2 924 Cornell University, Element, UC Berkeley, UC San Diego Canada, USA academia
StarGAN v2: Diverse Image Synthesis for Multiple Domains 916 NAVER South Korea industry
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection 899 Chinese Academy of Sciences, Chinese University of Hong Kong, National Laboratory of Pattern Recognition, SenseTime China academia
A Primer in BERTology: What we know about how BERT works 20 892 University of Copenhagen, University of Massachusetts Lowell Denmark, USA academia
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow 10 860 Princeton University USA academia
Multilingual Denoising Pre-training for Neural Machine Translation 1 859 Meta USA industry
Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection 850 Beijing University of Posts and Telecommunications, Chinese Academy of Sciences, National Laboratory of Pattern Recognition, University of Chinese Academy of Sciences, Westlake University China academia
Knowledge Distillation: A Survey 19 850 University of London, University of Sydney Australia, UK academia
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds 3 848 National University of Defense Technology, Sun Yat-sen University, University of Oxford China, UK academia
SuperGlue: Learning Feature Matching With Graph Neural Networks 10 839 ETH Zurich, Magic Leap Switzerland, USA industry
Generative Pretraining From Pixels 838 OpenAI USA industry
Pre-trained models for natural language processing: A survey 10 832 Fudan University China academia
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks 811 University of Tubingen Germany academia
Deep Learning for Person Re-identification: A Survey and Outlook 806 Beijing Institute of Technology, Inception Institute of AI, Salesforce, Singapore Management University, University of Surrey, Wuhan University China, Singapore, UAE, UK, USA academia, industry
Object-Contextual Representations for Semantic Segmentation 800 Chinese Academy of Sciences, Microsoft, University of Chinese Academy of Sciences China, USA industry
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains 14 774 Google, UC Berkeley, UC San Diego USA academia
Scaled-YOLOv4: Scaling Cross Stage Partial Network 758 Academia Sinica, Intel, Providence University Taiwan, USA academia, industry
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere 3 755 MIT USA academia
Fast is better than free: Revisiting adversarial training 744 Bosch, Carnegie Mellon University Germany, USA academia, industry
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting 35 741 Beihang University, Rutgers University, Sharjah Economic Development Department, UC Berkeley China, UAE, USA industry
CodeBERT: A Pre-Trained Model for Programming and Natural Languages 30 736 Harbin Institute of Technology, Microsoft, Sun Yat-sen University China, USA industry
Big Transfer (BiT): General Visual Representation Learning 51 704 Google USA industry
Pre-Trained Image Processing Transformer 3 703 Huawei, Peking University, Peng Cheng Laboratory, University of Sydney Australia, China academia
Rethinking Attention with Performers 38 697 Alan Turing Institute, DeepMind, Google, University of Cambridge UK, USA academia, industry
What makes for good views for contrastive learning 8 686 Brown University, Google, MIT USA academia
Score-Based Generative Modeling through Stochastic Differential Equations 54 684 Google, Stanford University USA industry
Graph Contrastive Learning with Augmentations 2 682 Google, Texas A&M University, University of Science and Technology of China, University of Texas at Austin China, USA academia
Interpreting the Latent Space of GANs for Semantic Face Editing 14 675 Chinese University of Hong Kong China academia
Linformer: Self-Attention with Linear Complexity 8 668 Meta USA industry
MaskGAN: Towards Diverse and Interactive Facial Image Manipulation 653 Chinese University of Hong Kong, SenseTime, University of Hong Kong China academia
Simple and Deep Graph Convolutional Networks 1 653 Alibaba Group, Fudan University, Renmin University of China China industry
REALM: Retrieval-Augmented Language Model Pre-Training 11 640 Google USA industry
Single Path One-Shot Neural Architecture Search with Uniform Sampling 1 627 Hong Kong University of Science and Technology, Megvii, Tsinghua University China industry
Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing 18 602 Microsoft USA industry
Tracking Objects as Points 3 589 Intel, University of Texas at Austin USA academia
Adaptive Federated Optimization 2 588 Google USA industry
Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference 7 581 Ludwig Maximilian University of Munich, Sulzer GmbH Germany academia
Making Pre-trained Language Models Better Few-shot Learners 13 576 MIT, Princeton University USA academia
Recipes for building an open-domain chatbot 12 575 Meta USA industry
Meshed-Memory Transformer for Image Captioning 572 University of Modena and Reggio Emilia Italy academia
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-Modal Pre-Training. 568 Microsoft, Peking University China, USA industry
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention 17 562 École Polytechnique Fédérale de Lausanne, Idiap Research Institute, University of Geneva, University of Washington Switzerland, USA academia
Learning to Simulate Complex Physics with Graph Networks 46 547 DeepMind, Stanford University UK, USA industry
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment. 546 Agency for Science, Technology and Research, MIT, University of Hong Kong China, Singapore, USA academia
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization 1 536 Carnegie Mellon University, DeepMind, Google UK, USA industry
On Adaptive Attacks to Adversarial Example Defenses 3 535 Google, MIT, Stanford University, University of Tubingen Germany, USA academia
Circle Loss: A Unified Perspective of Pair Similarity Optimization 534 Australian National University, Beihang University, Megvii, Tsinghua University Australia, China industry
Explaining machine learning classifiers through diverse counterfactual explanations. 527 Microsoft, University of Colorado Boulder USA academia
Efficient Transformers: A Survey 355 524 Google USA industry
Exploring Self-attention for Image Recognition 523 Chinese University of Hong Kong, Intel China, USA industry
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment