Meta & Continual Learning
Meta-learning, few-shot adaptation, continual/lifelong learning.
A topic in the Science corpus, drawn from 818 papers.
Trusted voices in Meta & Continual Learning
Ordered by the trust Meta & Continual Learning's own network concentrates on each researcher, most first.
- Anthony V. Robins — trusted by 360 researchers here
- Christoph H. Lampert — trusted by 309 researchers here
- Alexander Kolesnikov — trusted by 266 researchers here
- G. Sperl — trusted by 266 researchers here
- Sylvestre-Alvise Rebuffi — trusted by 265 researchers here
- Andreas S. Tolias — trusted by 206 researchers here
- Gido M. van de Ven — trusted by 204 researchers here
- Marcus Rohrbach — trusted by 219 researchers here
- Marc'Aurelio Ranzato — trusted by 199 researchers here
- Christopher Kanan — trusted by 172 researchers here
- Rahaf Aljundi — trusted by 182 researchers here
- Arslan Chaudhry — trusted by 181 researchers here
Most-cited papers in Meta & Continual Learning
Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.
- iCaRL: Incremental Classifier and Representation Learning (2016) — 4,930 citations
- A Survey on Multi-Task Learning (2017) — 3,013 citations
- A Survey on Deep Transfer Learning (2018) — 2,931 citations
- Deep Transfer Learning with Joint Adaptation Networks (2016) — 2,790 citations
- Meta-Learning in Neural Networks: A Survey (2020) — 2,723 citations
- A Continual Learning Survey: Defying Forgetting in Classification Tasks (2019, IEEE Transactions on Pattern Analysis and Machine Intelligence) — 2,435 citations
- pixelNeRF: Neural Radiance Fields from One or Few Images (2020) — 2,248 citations
- Tent: Fully Test-Time Adaptation by Entropy Minimization (2021) — 1,933 citations
- Multi-Task Learning as Multi-Objective Optimization (2018) — 1,788 citations
- Experience Replay for Continual Learning (2018, Neural Information Processing Systems) — 1,717 citations
- Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning (2019) — 1,715 citations
- Large Scale Incremental Learning (2019) — 1,535 citations
- Meta-Learning with Latent Embedding Optimization (2018, International Conference on Learning Representations) — 1,522 citations
- A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, IEEE Transactions on Pattern Analysis and Machine Intelligence) — 1,490 citations
- PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (2019) — 1,460 citations
- Learning a Unified Classifier Incrementally via Rebalancing (2019) — 1,402 citations
- Dark Experience for General Continual Learning: a Strong, Simple Baseline (2020) — 1,381 citations
- Few-Shot Learning with Graph Neural Networks (2017) — 1,368 citations
- Test-Time Training with Self-Supervision for Generalization under Distribution Shifts (2019) — 1,341 citations
- End-to-End Incremental Learning (2018) — 1,337 citations
- Learning to Prompt for Continual Learning (2021) — 1,330 citations
- Meta-SGD: Learning to Learn Quickly for Few Shot Learning (2017) — 1,259 citations
- Dynamic Few-Shot Visual Learning Without Forgetting (2018) — 1,219 citations
- The problem of concept drift: definitions and related work (2004) — 1,184 citations
- An Analysis of Active Learning Strategies for Sequence Labeling Tasks (2008) — 1,169 citations
- Meta Networks (2017) — 1,161 citations
- Bayesian Active Learning for Classification and Preference Learning (2011) — 1,125 citations
- Toward Optimal Active Learning through Sampling Estimation of Error Reduction (2001) — 1,072 citations
- Three scenarios for continual learning (2019) — 1,067 citations
- Gradient based sample selection for online continual learning (2019) — 1,049 citations
- Zero-Shot Learning — The Good, the Bad and the Ugly (2017) — 969 citations
- Learn++: an incremental learning algorithm for supervised neural networks (2001) — 946 citations
- Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference (2018) — 934 citations
- PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning (2020) — 909 citations
- DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers (2020) — 903 citations
- One-Shot Learning for Semantic Segmentation (2017) — 897 citations
- On Tiny Episodic Memories in Continual Learning (2019) — 896 citations
- Class-Incremental Learning: Survey and Performance Evaluation on Image Classification (2020) — 891 citations
- Bilevel Programming for Hyperparameter Optimization and Meta-Learning (2018) — 888 citations
- How to train your MAML (2018, International Conference on Learning Representations) — 887 citations
- DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning (2022) — 880 citations
- Few-Shot Object Detection via Feature Reweighting (2018) — 862 citations
- Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks (2019) — 845 citations
- Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables (2019) — 832 citations
- Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions (2018) — 830 citations
- Balanced Meta-Softmax for Long-Tailed Visual Recognition (2020) — 801 citations
- Learning in Nonstationary Environments: A Survey (2015) — 778 citations
- Low Data Drug Discovery with One-Shot Learning (2016) — 773 citations
- Latent Embeddings for Zero-Shot Classification (2016) — 750 citations
- Frustratingly Simple Few-Shot Object Detection (2020) — 747 citations
Most active researchers
By papers in this topic: a volume measure, not trust.
- Sergey Levine — 15 papers
- Tinne Tuytelaars — 14 papers
- Chelsea Finn — 14 papers
- Razvan Pascanu — 12 papers
- Joost van de Weijer — 12 papers
- Rahaf Aljundi — 12 papers
- Bing Liu — 12 papers
- Bernt Schiele — 11 papers
- Mehrdad Farajtabar — 10 papers
- Liyuan Wang — 8 papers
- Pieter Abbeel — 8 papers
- Trevor Darrell — 8 papers