Related papers: Task Attended Meta-Learning for Few-Shot Learning
Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges…
Deep neural networks (DNNs) have achieved state-of-the-art results on time series classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often-encountered practical scenario where access to labeled training data is…
Deep learning has achieved remarkable success in many machine learning tasks such as image classification, speech recognition, and game playing. However, these breakthroughs are often difficult to translate into real-world engineering…
Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-class that excel at quick adaptation to new tasks with limited…
Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines. However, the hierarchical…
Deep neural networks have been able to outperform humans in some cases like image recognition and image classification. However, with the emergence of various novel categories, the ability to continuously widen the learning capability of…
Meta-learning and other approaches to few-shot learning are widely studied for image recognition, and are increasingly applied to other vision tasks such as pose estimation and dense prediction. This naturally raises the question of whether…
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 method - by learning…
Data-efficient learning algorithms are essential in many practical applications where data collection is expensive, e.g., in robotics due to the wear and tear. To address this problem, meta-learning algorithms use prior experience about…
Developing meta-learning algorithms that are un-biased toward a subset of training tasks often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal solutions. In this paper, we introduce a new principled and…
This article proposes a meta-learning method for estimating the conditional average treatment effect (CATE) from a few observational data. The proposed method learns how to estimate CATEs from multiple tasks and uses the knowledge for…
In the context of few-shot learning, it is currently believed that a fixed pre-trained (PT) model, along with fine-tuning the final layer during evaluation, outperforms standard meta-learning algorithms. We re-evaluate these claims under an…
Currently, the state-of-the-art methods treat few-shot semantic segmentation task as a conditional foreground-background segmentation problem, assuming each class is independent. In this paper, we introduce the concept of meta-class, which…
Meta-learning methods have shown an impressive ability to train models that rapidly learn new tasks. However, these methods only aim to perform well in expectation over tasks coming from some particular distribution that is typically…
Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our…
Existing gradient-based meta-learning approaches to few-shot learning assume that all tasks have the same input feature space. However, in the real world scenarios, there are many cases that the input structures of tasks can be different,…
Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing works take the meta-learning approach, constructing a few-shot learner that can learn from few-shot examples to generate a classifier.…
Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods…
Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem in large-scale supervised classification, little has been done to overcome…
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…