Related papers: BaSAL: Size-Balanced Warm Start Active Learning fo…
Active learning aims to reduce labeling efforts by selectively asking humans to annotate the most important data points from an unlabeled pool and is an example of human-machine interaction. Though active learning has been extensively…
Current methods for LIDAR semantic segmentation are not robust enough for real-world applications, e.g., autonomous driving, since it is closed-set and static. The closed-set assumption makes the network only able to output labels of…
Batch active learning (BAL) is a crucial technique for reducing labeling costs and improving data efficiency in training large-scale deep learning models. Traditional BAL methods often rely on metrics like Mahalanobis Distance to balance…
Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely…
State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…
Annotating datasets for object detection is an expensive and time-consuming endeavor. To minimize this burden, active learning (AL) techniques are employed to select the most informative samples for annotation within a constrained…
Developed to alleviate prohibitive labeling costs, active learning (AL) methods aim to reduce label complexity in supervised learning. While recent work has demonstrated the benefit of using AL in combination with large pre-trained language…
This paper introduces an active learning (AL) framework for anomalous sound detection (ASD) in machine condition monitoring system. Typically, ASD models are trained solely on normal samples due to the scarcity of anomalous data, leading to…
Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dominant label per…
The objective of active learning (AL) is to train classification models with less number of labeled instances by selecting only the most informative instances for labeling. The AL algorithms designed for other data types such as images and…
Recently, Convolutional Neural Networks (CNNs) have shown unprecedented success in the field of computer vision, especially on challenging image classification tasks by relying on a universal approach, i.e., training a deep model on a…
Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label new selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due…
Active learning has proven to be useful for minimizing labeling costs by selecting the most informative samples. However, existing active learning methods do not work well in realistic scenarios such as imbalance or rare classes,…
This paper proposes SemCal: an automatic, targetless, extrinsic calibration algorithm for a LiDAR and camera system using semantic information. We leverage a neural information estimator to estimate the mutual information (MI) of semantic…
Active preference learning offers an efficient approach to modeling preferences, but it is hindered by the cold-start problem, which leads to a marked decline in performance when no initial labeled data are available. While cold-start…
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…
During recent years, active learning has evolved into a popular paradigm for utilizing user's feedback to improve accuracy of learning algorithms. Active learning works by selecting the most informative sample among unlabeled data and…
As deep learning continues to evolve, the need for data efficiency becomes increasingly important. Considering labeling large datasets is both time-consuming and expensive, active learning (AL) provides a promising solution to this…
This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. While the recent CISS algorithms utilize variants of the knowledge distillation (KD) technique to tackle the problem, they…
We introduce a new and improved characterization of the label complexity of disagreement-based active learning, in which the leading quantity is the version space compression set size. This quantity is defined as the size of the smallest…