Related papers: Active Learning for Skewed Data Sets
Object detection (OD), a crucial vision task, remains challenged by the lack of large training datasets with precise object localization labels. In this work, we propose ALWOD, a new framework that addresses this problem by fusing active…
Hard interaction learning between source sequences and their next targets is challenging, which exists in a myriad of sequential prediction tasks. During the training process, most existing methods focus on explicitly hard interactions…
In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new…
Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework,…
Open-set supervised anomaly detection (OSAD) - a recently emerging anomaly detection area - aims at utilizing a few samples of anomaly classes seen during training to detect unseen anomalies (i.e., samples from open-set anomaly classes),…
Most prior work on active learning of classifiers has focused on sequentially selecting one unlabeled example at a time to be labeled in order to reduce the overall labeling effort. In many scenarios, however, it is desirable to label an…
Active Learning (AL) aims to enhance the performance of deep models by selecting the most informative samples for annotation from a pool of unlabeled data. Despite impressive performance in closed-set settings, most AL methods fail in…
Active learning(AL), which serves as the representative label-efficient learning paradigm, has been widely applied in resource-constrained scenarios. The achievement of AL is attributed to acquisition functions, which are designed for…
We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement. Instead of requesting labels from human oracle, our method automatically…
An ever increasing volume of data is nowadays becoming available in a streaming manner in many application areas, such as, in critical infrastructure systems, finance and banking, security and crime and web analytics. To meet this new…
Fine-grained classification remains a very challenging problem, because of the absence of well-labeled training data caused by the high cost of annotating a large number of fine-grained categories. In the extreme case, given a set of test…
Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines. Active ML aims to address this issue by designing learning algorithms that automatically and adaptively select the most informative…
Active learning is a type of sequential design for supervised machine learning, in which the learning algorithm sequentially requests the labels of selected instances from a large pool of unlabeled data points. The objective is to produce a…
Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence…
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…
Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators. We study and propose a novel framework that formulates batch active learning from the sparse approximation's…
Active domain adaptation (ADA) studies have mainly addressed query selection while following existing domain adaptation strategies. However, we argue that it is critical to consider not only query selection criteria but also domain…
Active Learning (AL) is a family of machine learning (ML) algorithms that predates the current era of artificial intelligence. Unlike traditional approaches that require labeled samples for training, AL iteratively selects unlabeled samples…
Active Learning (AL) is a human-in-the-loop framework to interactively and adaptively label data instances, thereby enabling significant gains in model performance compared to random sampling. AL approaches function by selecting the hardest…
Many pairwise classification tasks, such as paraphrase detection and open-domain question answering, naturally have extreme label imbalance (e.g., $99.99\%$ of examples are negatives). In contrast, many recent datasets heuristically choose…