Related papers: Active learning for imbalanced data under cold sta…
Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only…
Given a labeled training set and a collection of unlabeled data, the goal of active learning (AL) is to identify the best unlabeled points to label. In this comprehensive study, we analyze the performance of a variety of AL algorithms on…
Often, labeling large amount of data is challenging due to high labeling cost limiting the application domain of deep learning techniques. Active learning (AL) tackles this by querying the most informative samples to be annotated among…
Data stream classification is an important problem in the field of machine learning. Due to the non-stationary nature of the data where the underlying distribution changes over time (concept drift), the model needs to continuously adapt to…
Pretrained on web-scale open data, VLMs offer powerful capabilities for solving downstream tasks after being adapted to task-specific labeled data. Yet, data labeling can be expensive and may demand domain expertise. Active Learning (AL)…
Pool-based active learning (AL) aims to optimize the annotation process (i.e., labeling) as the acquisition of annotations is often time-consuming and therefore expensive. For this purpose, an AL strategy queries annotations intelligently…
In many machine learning applications, labeling datasets can be an arduous and time-consuming task. Although research has shown that semi-supervised learning techniques can achieve high accuracy with very few labels within the field of…
Meta-learning algorithms for active learning are emerging as a promising paradigm for learning the ``best'' active learning strategy. However, current learning-based active learning approaches still require sufficient training data so as to…
Active Learning aims to optimize performance while minimizing annotation costs by selecting the most informative samples from an unlabelled pool. Traditional uncertainty sampling often leads to sampling bias by choosing similar uncertain…
Multi-domain learning (MDL) refers to learning a set of models simultaneously, where each model is specialized to perform a task in a particular domain. Generally, a high labeling effort is required in MDL, as data needs to be labeled by…
Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless, it remains unclear how selected data impacts the test…
This paper proposes an active learning (AL) algorithm to solve regression problems based on inverse-distance weighting functions for selecting the feature vectors to query. The algorithm has the following features: (i) supports both…
Classification algorithms to mine data stream have been extensively studied in recent years. However, a lot of these algorithms are designed for supervised learning which requires labeled instances. Nevertheless, the labeling of the data is…
Active learning (AL) reduces the amount of labeled data needed to train a machine learning model by intelligently choosing which instances to label. Classic pool-based AL requires all data to be present in a datacenter, which can be…
Adversarial training is an important topic in robust deep learning, but the community lacks attention to its practical usage. In this paper, we aim to resolve a real-world challenge, i.e., training a model on an imbalanced and noisy dataset…
With the goal of making deep learning more label-efficient, a growing number of papers have been studying active learning (AL) for deep models. However, there are a number of issues in the prevalent experimental settings, mainly stemming…
Human behavior expression and experience are inherently multi-modal, and characterized by vast individual and contextual heterogeneity. To achieve meaningful human-computer and human-robot interactions, multi-modal models of the users…
Machine Learning (ML) is widely used to automatically extract meaningful information from Electronic Health Records (EHR) to support operational, clinical, and financial decision-making. However, ML models require a large number of…
While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of data annotation, active learning has been proposed to…
We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (labelled observations) and the cost of prediction errors. We…