Browse SoTA > Methodology > Meta-Learning

# Meta-Learning Edit

274 papers with code · Methodology

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

# Neural Complexity Measures

7 Aug 2020

While various complexity measures for diverse model classes have been proposed, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven to be challenging.

# Few-shot Classification via Adaptive Attention

6 Aug 2020

To be specific, we devise a simple and efficient meta-reweighting strategy to adapt the sample representations and generate soft attention to refine the representation such that the relevant features from the query and support samples can be extracted for a better few-shot classification.

# Data-driven Meta-set Based Fine-Grained Visual Classification

6 Aug 2020

To this end, we propose a data-driven meta-set based approach to deal with noisy web images for fine-grained recognition.

# Improving End-to-End Speech-to-Intent Classification with Reptile

5 Aug 2020

In this paper, we suggest improving the generalization performance of SLU models with a non-standard learning algorithm, Reptile.

# A Neural-Symbolic Framework for Mental Simulation

5 Aug 2020

We present a neural-symbolic framework for observing the environment and continuously learning visual semantics and intuitive physics to reproduce them in an interactive simulation.

# Learning to Purify Noisy Labels via Meta Soft Label Corrector

3 Aug 2020

By viewing the label correction procedure as a meta-process and using a meta-learner to automatically correct labels, we could adaptively obtain rectified soft labels iteratively according to current training problems without manually preset hyper-parameters.

# Meta-DRN: Meta-Learning for 1-Shot Image Segmentation

1 Aug 2020

In this paper, we propose a novel lightweight CNN architecture for 1-shot image segmentation.

# Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records

1 Aug 2020

The goal is to facilitate the learning process in the target segments even facing a shortage of related training data by leveraging the learned knowledge from data-sufficient source segments.

# L$^2$C -- Learning to Learn to Compress

31 Jul 2020

In a second phase, the Model-Agnostic Meta-learning approach is adapted to the specific case of image compression, where the inner-loop performs latent tensor overfitting, and the outer loop updates both encoder and decoder neural networks based on the overfitting performance.

# Learning from Few Samples: A Survey

30 Jul 2020

Deep neural networks have been able to outperform humans in some cases like image recognition and image classification.