paper-with-me

홈 › Papers

Meta-Learning Initializations for Image Segmentation

2019-12-13 · Sean M. Hendryx, Andrew B. Leach, Paul D. Hein, Clayton T. Morrison

We extend first-order model agnostic meta-learning algorithms (including FOMAML and Reptile) to image segmentation, present a novel neural network architecture built for fast learning which we call EfficientLab, and leverage a formal definition of the test error of meta-learning algorithms to decrease error on out of distribution tasks. We show state of the art results on the FSS-1000 dataset by meta-training EfficientLab with FOMAML and using Bayesian optimization to infer the optimal test-time adaptation routine hyperparameters. We also construct a small benchmark dataset, FP-k, for the empirical study of how meta-learning systems perform in both few- and many-shot settings. On the FP-k dataset, we show that meta-learned initializations provide value for canonical few-shot image segmentation but their performance is quickly matched by conventional transfer learning with performance being equal beyond 10 labeled examples. Our code, meta-learned model, and the FP-k dataset are available at https://github.com/ml4ai/mliis .

📄 PDF Abstract BibTeX arXiv:1912.06290

Code (1)

ml4ai/mliis 공식 구현 tf

Tasks

Bayesian OptimizationFew-Shot Image ClassificationFew-Shot LearningImage ClassificationImage SegmentationMeta-LearningSegmentationSemantic SegmentationTest-time AdaptationTransfer Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction

2020-06-12 · ICML Workshop LifelongML 2020 7 · Cuong Q. Nguyen, Constantine Kreatsoulas, Kim M. Branson

Building $\textit{in silico}$ models to predict chemical properties and activities is a crucial step in drug discovery. However, limited labeled data often hinders the application of deep learning in this setting. Meanwh…

Drug DiscoveryFew-Shot LearningMeta-LearningMolecular Property Prediction+1

MetaInit: Initializing learning by learning to initialize

2019-12-01 · NeurIPS 2019 12 · Yann N. Dauphin, Samuel Schoenholz

Deep learning models frequently trade handcrafted features for deep features learned with much less human intervention using gradient descent. While this paradigm has been enormously successful, deep networks are often d…

Meta-Learning

Meta-Learning Initializations for Low-Resource Drug Discovery

2020-03-12 · Cuong Q. Nguyen, Constantine Kreatsoulas, Kim M. Branson

Building in silico models to predict chemical properties and activities is a crucial step in drug discovery. However, drug discovery projects are often characterized by limited labeled data, hindering the applications of…

Drug DiscoveryFew-Shot LearningMeta-Learning

Modulating transfer between tasks in gradient-based meta-learning

2019-05-01 · ICLR 2019 5 · Erin Grant, Ghassen Jerfel, Katherine Heller, Thomas L. Griffiths

Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is not mutually beneficial, for instance, …

DiversityInductive BiasMeta-Learning

XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage

2024-03-11 · Jae-Jun Lee, Sung Whan Yoon

Meta-learning, which pursues an effective initialization model, has emerged as a promising approach to handling unseen tasks. However, a limitation remains to be evident when a meta-learner tries to encompass a wide rang…

Inductive BiasMeta-Learning