Related papers: Active Class Incremental Learning for Imbalanced D…
Training deep learning models on medical datasets that perform well for all classes is a challenging task. It is often the case that a suboptimal performance is obtained on some classes due to the natural class imbalance issue that comes…
Model learning from class imbalanced training data is a long-standing and significant challenge for machine learning. In particular, existing deep learning methods consider mostly either class balanced data or moderately imbalanced data in…
Learning from imbalanced data is a challenging task. Standard classification algorithms tend to perform poorly when trained on imbalanced data. Some special strategies need to be adopted, either by modifying the data distribution or by…
Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major obstacles making it challenging to implement for real life…
Active learning (AL) is a widely-used training strategy for maximizing predictive performance subject to a fixed annotation budget. In AL one iteratively selects training examples for annotation, often those for which the current model is…
Data-driven learning algorithms are employed in many online applications, in which data become available over time, like network monitoring, stock price prediction, job applications, etc. The underlying data distribution might evolve over…
Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained…
Most meta-learning approaches assume the existence of a very large set of labeled data available for episodic meta-learning of base knowledge. This contrasts with the more realistic continual learning paradigm in which data arrives…
This paper presents a practical and simple yet efficient method to effectively deal with the catastrophic forgetting for Class Incremental Learning (CIL) tasks. CIL tends to learn new concepts perfectly, but not at the expense of…
Active learning emerged as an alternative to alleviate the effort to label huge amount of data for data hungry applications (such as image/video indexing and retrieval, autonomous driving, etc.). The goal of active learning is to…
Instance-incremental learning (IIL) focuses on learning continually with data of the same classes. Compared to class-incremental learning (CIL), the IIL is seldom explored because IIL suffers less from catastrophic forgetting (CF). However,…
Due to the model aging problem, Deep Neural Networks (DNNs) need updates to adjust them to new data distributions. The common practice leverages incremental learning (IL), e.g., Class-based Incremental Learning (CIL) that updates output…
Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e.…
Meta-Learning (ML) has proven to be a useful tool for training Few-Shot Learning (FSL) algorithms by exposure to batches of tasks sampled from a meta-dataset. However, the standard training procedure overlooks the dynamic nature of the…
Many medical datasets have recently been created for medical image segmentation tasks, and it is natural to question whether we can use them to sequentially train a single model that (1) performs better on all these datasets, and (2)…
Automated Machine Learning has grown very successful in automating the time-consuming, iterative tasks of machine learning model development. However, current methods struggle when the data is imbalanced. Since many real-world datasets are…
We present novel active learning strategies dedicated to providing a solution to the cold start stage, i.e. initializing the classification of a large set of data with no attached labels. Moreover, proposed strategies are designed to handle…
Active learning (AL) algorithms aim to identify an optimal subset of data for annotation, such that deep neural networks (DNN) can achieve better performance when trained on this labeled subset. AL is especially impactful in industrial…
We present a novel Balanced Incremental Model Agnostic Meta Learning system (BI-MAML) for learning multiple tasks. Our method implements a meta-update rule to incrementally adapt its model to new tasks without forgetting old tasks. Such a…
Human intelligence gradually accepts new information and accumulates knowledge throughout the lifespan. However, deep learning models suffer from a catastrophic forgetting phenomenon, where they forget previous knowledge when acquiring new…