Related papers: What Matters For Meta-Learning Vision Regression T…
Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge. However, the bottleneck of current meta-learning algorithms is the requirement of a…
Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be…
Deep learning methods have been successful in solving tasks in machine learning and have made breakthroughs in many sectors owing to their ability to automatically extract features from unstructured data. However, their performance relies…
We consider a new problem of few-shot learning of compact models. Meta-learning is a popular approach for few-shot learning. Previous work in meta-learning typically assumes that the model architecture during meta-training is the same as…
Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We…
Utilizing task-invariant knowledge acquired from related tasks as prior information, meta-learning offers a principled approach to learning a new task with limited data records. Sample-efficient adaptation of this prior information is a…
Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks. In this work, we argue that this is due to the lack of a good representation for meta-learning, and propose…
In few-shot learning, classifiers are expected to generalize to unseen classes given only a small number of instances of each new class. One of the popular solutions to few-shot learning is metric-based meta-learning. However, it highly…
Using single-task deep learning methods to reconstruct Magnetic Resonance Imaging (MRI) data acquired with different imaging sequences is inherently challenging. The trained deep learning model typically lacks generalizability, and the…
Recent work has shown the efficiency of deep learning models such as Fully Convolutional Networks (FCN) or Recurrent Neural Networks (RNN) to deal with Time Series Regression (TSR) problems. These models sometimes need a lot of data to be…
Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification, segmentation and detection. The low-shot learning…
Few-shot classification aims to recognize unseen classes with few labeled samples from each class. Many meta-learning models for few-shot classification elaborately design various task-shared inductive bias (meta-knowledge) to solve such…
The goal of meta-learning is to generalize to new tasks and goals as quickly as possible. Ideally, we would like approaches that generalize to new goals and tasks on the first attempt. Toward that end, we introduce contextual planning…
Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…
Deep Learning has become interestingly popular in computer vision, mostly attaining near or above human-level performance in various vision tasks. But recent work has also demonstrated that these deep neural networks are very vulnerable to…
We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training…
In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A…
Deep neural networks (DNNs) have revolutionized artificial intelligence but often lack performance when faced with out-of-distribution (OOD) data, a common scenario due to the inevitable domain shifts in real-world applications. This…
Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. This prevents the feasibility of deployment on different input image resolutions for a specific model. To…
Meta-learning is a powerful paradigm for few-shot learning. Although with remarkable success witnessed in many applications, the existing optimization based meta-learning models with over-parameterized neural networks have been evidenced to…