paper-with-me

홈 › Papers

Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks

2020-02-17 · ICML 2020 1 · Micah Goldblum, Steven Reich, Liam Fowl, Renkun Ni, Valeriia Cherepanova, Tom Goldstein

Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the underlying mechanics of meta-learning and the difference between models trained using meta-learning and models which are trained classically. In doing so, we introduce and verify several hypotheses for why meta-learned models perform better. Furthermore, we develop a regularizer which boosts the performance of standard training routines for few-shot classification. In many cases, our routine outperforms meta-learning while simultaneously running an order of magnitude faster.

📄 PDF Abstract BibTeX arXiv:2002.06753

Code (1)

goldblum/FeatureClustering 공식 구현 pytorch

Tasks

ClassificationGeneral ClassificationMeta-Learning

Similar Papers 제목 키워드 기반

Channel Importance Matters in Few-Shot Image Classification

2022-06-16 · Xu Luo, Jing Xu, Zenglin Xu

Few-Shot Learning (FSL) requires vision models to quickly adapt to brand-new classification tasks with a shift in task distribution. Understanding the difficulties posed by this task distribution shift is central to FSL.…

Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage Classification

Exploring the Similarity of Representations in Model-Agnostic Meta-Learning

2021-05-12 · ICLR Workshop Learning_to_Learn 2021 5 · Thomas Goerttler, Klaus Obermayer

In past years model-agnostic meta-learning (MAML) has been one of the most promising approaches in meta-learning. It can be applied to different kinds of problems, e.g., reinforcement learning, but also shows good result…

Few-Shot LearningMeta-Learning

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML

2019-09-19 · ICLR 2020 1 · Aniruddh Raghu, Maithra Raghu, Samy Bengio, Oriol Vinyals

An important research direction in machine learning has centered around developing meta-learning algorithms to tackle few-shot learning. An especially successful algorithm has been Model Agnostic Meta-Learning (MAML), a …

Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage Classification+2

Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition

2021-01-08 · ICCV 2021 10 · Xueting Zhang, Debin Meng, Henry Gouk, Timothy Hospedales

Current state-of-the-art few-shot learners focus on developing effective training procedures for feature representations, before using simple, e.g. nearest centroid, classifiers. In this paper, we take an orthogonal appr…

Cross-Domain Few-Shotcross-domain few-shot learningFew-Shot Image ClassificationFew-Shot Learning+1

Does MAML Only Work via Feature Re-use? A Data Centric Perspective

2021-12-24 · Brando Miranda, Yu-Xiong Wang, Sanmi Koyejo

Recent work has suggested that a good embedding is all we need to solve many few-shot learning benchmarks. Furthermore, other work has strongly suggested that Model Agnostic Meta-Learning (MAML) also works via this same …

Few-Shot LearningMeta-Learning