https://github.com/Deepest-Project/meta-learning-study
Deepest Season 6 Meta-Learning study papers plus alpha
https://github.com/Deepest-Project/meta-learning-study
few-shot-learning maml meta-learning papers prototypical-networks shot-learning
Last synced: 18 days ago
JSON representation
Deepest Season 6 Meta-Learning study papers plus alpha
- Host: GitHub
- URL: https://github.com/Deepest-Project/meta-learning-study
- Owner: Deepest-Project
- Created: 2019-11-29T12:12:12.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2020-03-04T05:39:59.000Z (almost 6 years ago)
- Last Synced: 2024-06-25T05:35:31.094Z (over 1 year ago)
- Topics: few-shot-learning, maml, meta-learning, papers, prototypical-networks, shot-learning
- Size: 33.2 KB
- Stars: 23
- Watchers: 2
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Meta-Learning-Study
Deepest Season 6 Meta-Learning study papers plus alpha
Those who are new to meta-learning, I recommend to start with reading these
+ Model-agnostic Meta-Learning for Fast Adaptation of Deep Networks
+ Prototypical Networks for Few-shot Learning
+ ICML 2019 Meta-Learning Tutorial [[link]](https://sites.google.com/view/icml19metalearning)
+ CS 330: Deep Multi-Task and Meta Learning [[link]](http://cs330.stanford.edu/)
## Optimization-based Meta-Learning
+ Model-agnostic Meta-Learning for Fast Adaptation of Deep Networks, (ICML 2017), [[link]](https://arxiv.org/abs/1703.03400)
+ Meta-Learning with Latent Embedding Optimization, (ICLR 2019), [[link]](https://arxiv.org/abs/1807.05960)
+ How to Train Your MAML, (ICLR 2019), [[link]](https://arxiv.org/abs/1810.09502)
+ Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML, (NeurIPs 2019 workshop)[[link]](https://arxiv.org/abs/1909.09157)
+ Meta-Learning with Implicit Gradients, (NIPS 2019), [[link]](https://arxiv.org/abs/1909.04630)
+ Meta-Learning with Warped Gradient Descent, (ICLR 2020), [[link]](https://openreview.net/forum?id=rkeiQlBFPB)
## Metric-Learning based Meta-Learning
+ Prototypical Networks for Few-shot Learning, (NIPS 2017), [[link]](https://arxiv.org/abs/1703.05175)
+ Learning to Compare: Relation Network for Few-Shot Learning, (CVPR 2018), [[link]](https://arxiv.org/abs/1711.06025)
+ TADAM: Task dependent adaptive metric for improved few-shot learning, (NIPS 2018)[[link]](https://arxiv.org/abs/1805.10123)
+ Infinite Mixture Prototypes for Few-Shot Learning, (ICML 2019), [[link]](https://arxiv.org/abs/1902.04552)
## Black-box adaptation based Meta-Learning
+ One-shot Learning with Memory-Augmented Neural Networks, (ArXiv 2016), [[link]](https://arxiv.org/abs/1605.06065)
+ Learning to learn by gradient descent by gradient descent, (NIPS 2016), [[link]](https://arxiv.org/abs/1606.04474)
+ A Simple Neural Attentive Meta-Learner, (ICLR 2018), [[link]](https://arxiv.org/abs/1707.03141)
+ Meta-Learning with Differentiable Convex Optimization, (CVPR 2019), [[link]](https://arxiv.org/abs/1904.03758)
## Bayesian Approaches
+ Towards a Neural Statistician, (ICLR 2017), [[link]](https://arxiv.org/abs/1606.02185)
+ Conditional Neural Processes, (ICML 2018), [[link]](https://arxiv.org/abs/1807.01613)
+ Probabilistic Model-Agnostic Meta-Learning, (NIPS 2018), [[link]](https://arxiv.org/abs/1806.02817)
## Generation
+ Few-Shot Adversarial Learning of Realistic Neural Talking Head Models, (ICCV 2019), [[link]](https://arxiv.org/abs/1905.08233)
+ Few-Shot Adaptive Gaze Estimation, (ICCV 2019), [[link]](https://arxiv.org/abs/1905.01941)
+ MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets, (AAAI 2020), [[link]](https://arxiv.org/abs/1911.08139)
+ MetaPix: Few-Shot Video Retargeting, (ICLR 2020), [[link]](https://openreview.net/forum?id=SJx1URNKwH)
## Unsupervised, Representation
+ Unsupervised Learning via Meta-Learning, (ICLR 2019), [[link]](https://arxiv.org/abs/1810.02334)
+ Meta-Learning Update Rules for Unsupervised Representation Learning, (ICLR 2019), [[link]](https://arxiv.org/abs/1804.00222)
## Realistic Setting
+ A Closer Look at Few-shot Classification, (ICLR 2019), [[link]](https://arxiv.org/abs/1904.04232)
+ Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples, (ICLR 2020 under review), [[link]](https://arxiv.org/abs/1903.03096)
+ Meta-Learning without Memorization, (ICLR2020), [[link]](https://arxiv.org/abs/1912.03820)
## Object Detection and Segmentation
+ CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning, (CVPR 2019), [[link]](https://arxiv.org/abs/1903.02351)
+ Few-shot Object Detection via Feature Reweighting, (ICCV 2019), [[link]](https://arxiv.org/abs/1812.01866)
+ Meta-Learning to Detect Rare Objects, (ICCV 2019), [[link]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Meta-Learning_to_Detect_Rare_Objects_ICCV_2019_paper.pdf)
## Self-Supervised Learning
+ Boosting Few-Shot Visual Learning with Self-Supervision, (ICCV 2019), [[link]](https://arxiv.org/abs/1906.05186)
+ Charting the Right Manifold: Manifold Mixup for Few-shot Learning, (ArXiv 2019), [[link]](https://arxiv.org/abs/1907.12087)
## Before 2016