Related papers: Active Learning for the Optimal Design of Multinom…
The goal of active learning is to achieve the same accuracy achievable by passive learning, while using much fewer labels. Exponential savings in terms of label complexity have been proved in very special cases, but fundamental lower bounds…
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…
Pre-trained Vision Language Models (VLMs) have demonstrated notable progress in various zero-shot tasks, such as classification and retrieval. Despite their performance, because improving performance on new tasks requires task-specific…
Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…
Conventional active learning algorithms assume a single labeler that produces noiseless label at a given, fixed cost, and aim to achieve the best generalization performance for given classifier under a budget constraint. However, in many…
Machine learning in medical imaging during clinical routine is impaired by changes in scanner protocols, hardware, or policies resulting in a heterogeneous set of acquisition settings. When training a deep learning model on an initial…
Acquisition of labeled training samples for affective computing is usually costly and time-consuming, as affects are intrinsically subjective, subtle and uncertain, and hence multiple human assessors are needed to evaluate each affective…
Imaging in clinical routine is subject to changing scanner protocols, hardware, or policies in a typically heterogeneous set of acquisition hardware. Accuracy and reliability of deep learning models suffer from those changes as data and…
Uncertainty estimation is important for interpreting the trustworthiness of machine learning models in many applications. This is especially critical in the data-driven active learning setting where the goal is to achieve a certain accuracy…
We consider an active learning setting where the algorithm has access to a large pool of unlabeled data and a small pool of labeled data. In each iteration, the algorithm chooses few unlabeled data points and obtains their labels from an…
Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data…
We design an active learning algorithm for cost-sensitive multiclass classification: problems where different errors have different costs. Our algorithm, COAL, makes predictions by regressing to each label's cost and predicting the…
Active learning aims to train a classifier as fast as possible with as few labels as possible. The core element in virtually any active learning strategy is the criterion that measures the usefulness of the unlabeled data based on which new…
Machine Learning requires large amounts of labeled data to fit a model. Many datasets are already publicly available, nevertheless forcing application possibilities of machine learning to the domains of those public datasets. The…
Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates…
Deep Neural Networks trained in a fully supervised fashion are the dominant technology in perception-based autonomous driving systems. While collecting large amounts of unlabeled data is already a major undertaking, only a subset of it can…
An active learner is given a hypothesis class, a large set of unlabeled examples and the ability to interactively query labels to an oracle of a subset of these examples; the goal of the learner is to learn a hypothesis in the class that…
Modern machine learning models require large labelled datasets to achieve good performance, but manually labelling large datasets is expensive and time-consuming. The data programming paradigm enables users to label large datasets…
Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by using both labeled and unlabeled data during model training…
We analyze the problem of active covering, where the learner is given an unlabeled dataset and can sequentially label query examples. The objective is to label query all of the positive examples in the fewest number of total label queries.…