Han-Jia Ye

Artificial Intelligence · 2015–2024

A researcher in the Science corpus: 25 papers; trusts 2,729 researchers and is trusted by 45 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 1,275 citations into it; #4,714 of 35,345 by trust here, #4,860 by citations
• Computer Vision and Pattern Recognition — 1,018 citations into it; #4,399 of 21,575 by trust here, #3,955 by citations
• Meta & Continual Learning — 493 citations into it; #159 of 1,041 by trust here, #161 by citations
• Representation & Self-Supervised Learning — 450 citations into it; #1,042 of 3,145 by trust here, #1,068 by citations
• Radiology, Nuclear Medicine and Imaging — 164 citations into it; #1,483 of 3,265 by trust here, #1,376 by citations
• Optimization & Training — 153 citations into it
• Model Architectures — 88 citations into it
• Evaluation & Benchmarks — 82 citations into it

Whom Han-Jia Ye 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. Oriol Vinyals
6. Ross B. Girshick
7. Chelsea Finn
8. Yoshua Bengio
9. Ilya Sutskever
10. Yann LeCun

Who trusts Han-Jia Ye overall

1. Da-Wei Zhou
2. De-chuan Zhan
3. Chi Zhang
4. Wei-Lun Chao
5. Fu-Yun Wang
6. Qiwen Wang
7. Hexiang Hu
8. Yaoyao Liu
9. Ji Zhang
10. Qianru Sun

Papers from Han-Jia Ye's perspective

Ordered by how strongly the researchers Han-Jia Ye 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. ImageNet Large Scale Visual Recognition Challenge
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions (2018) — 830 citations
• Forward Compatible Few-Shot Class-Incremental Learning (2022) — 288 citations
• Learning Placeholders for Open-Set Recognition (2021) — 267 citations
• Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks (2022) — 199 citations
• Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning (2024) — 162 citations
• Deep Class-Incremental Learning: A Survey (2023) — 133 citations
• Class-Incremental Learning: A Survey (2023) — 380 citations
• A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning (2022) — 241 citations
• FOSTER: Feature Boosting and Compression for Class-Incremental Learning (2022) — 428 citations
• Identifying Ambiguous Similarity Conditions via Semantic Matching (2022) — 9 citations
• How to Train Your MAML to Excel in Few-Shot Classification (2021) — 65 citations
• Tailoring Embedding Function to Heterogeneous Few-Shot Tasks by Global and Local Feature Adaptors (2021) — 29 citations
• Co-Transport for Class-Incremental Learning (2021) — 100 citations
• PyCIL: a Python toolbox for class-incremental learning (2021) — 145 citations
• Contextualizing Multiple Tasks via Learning to Decompose (2021) — 5 citations
• Few-Shot Learning With a Strong Teacher (2021) — 82 citations
• Multi-Instance Learning With Emerging Novel Class (2021) — 31 citations
• Revisiting Meta-Learning as Supervised Learning (2020) — 24 citations
• Heterogeneous Few-Shot Model Rectification With Semantic Mapping (2020) — 36 citations
• Learning Classifier Synthesis for Generalized Few-Shot Learning (2019) — 11 citations