Related papers: Active Learning for Planet Habitability Classifica…

A principle bottleneck in image classification is the large number of training examples needed to train a classifier. Using active learning, we can reduce the number of training examples to teach a CNN classifier by strategically selecting…

Training multimodal networks requires a vast amount of data due to their larger parameter space compared to unimodal networks. Active learning is a widely used technique for reducing data annotation costs by selecting only those samples…

Supervised machine learning relies on the availability of good labelled data for model training. Labelled data is acquired by human annotation, which is a cumbersome and costly process, often requiring subject matter experts. Active…

Pool-based sequential active learning for regression (ALR) optimally selects a small number of samples sequentially from a large pool of unlabeled samples to label, so that a more accurate regression model can be constructed under a given…

We consider the unsupervised learning problem of assigning labels to unlabeled data. A naive approach is to use clustering methods, but this works well only when data is properly clustered and each cluster corresponds to an underlying…

Habitability is a measure of an environment's potential to support life, and a habitable exoplanet supports liquid water on its surface. However, a planet's success in maintaining liquid water on its surface is the end result of a complex…

Recent advances in machine learning have led to increased deployment of black-box classifiers across a wide variety of applications. In many such situations there is a critical need to both reliably assess the performance of these…

Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that…

Active learning is a learning strategy whereby the machine learning algorithm actively identifies and labels data points to optimize its learning. This strategy is particularly effective in domains where an abundance of unlabeled data…

Active learning has emerged as a promising approach to reduce the substantial annotation burden in 3D object detection tasks, spurring several initiatives in outdoor environments. However, its application in indoor environments remains…

Real-world fine-grained visual retrieval often requires discovering a rare concept from large unlabeled collections with minimal supervision. This is especially critical in biodiversity monitoring, ecological studies, and long-tailed visual…

Change detection is a major task in remote sensing which consists in finding all the occurrences of changes in multi-temporal satellite or aerial images. The success of existing methods, and particularly deep learning ones, is tributary to…

Open pit mines left many regions worldwide inhospitable or uninhabitable. To put these regions back into use, entire stretches of land must be renaturalized. For the sustainable subsequent use or transfer to a new primary use, many…

We study the problem of actively learning a classifier with a low calibration error. One of the most popular Acquisition Functions (AFs) in pool-based Active Learning (AL) is querying by the model's uncertainty. However, we recognize that…

The dynamic nature of life's ability to thrive in diverse and changing planetary environments suggests that habitability and survival depend on the evolutionary path and life adaptation to environmental conditions. Here we explore such…

With thousands of exoplanets now identified, the characterization of habitable planets and the potential identification of inhabited ones is a major challenge for the coming decades. We review the current working definition of habitable…

We address the problem of active learning under label shift: when the class proportions of source and target domains differ. We introduce a "medial distribution" to incorporate a tradeoff between importance weighting and class-balanced…

Important tasks like record linkage and extreme classification demonstrate extreme class imbalance, with 1 minority instance to every 1 million or more majority instances. Obtaining a sufficient sample of all classes, even just to achieve…

Pool-based sampling in active learning (AL) represents a key framework for an-notating informative data when dealing with deep learning models. In this paper, we present a novel pipeline for pool-based Active Learning. Unlike most previous…

Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure. Active learning addresses this challenge by striving for optimum…