Related papers: Box-Level Active Detection

Active learning improves annotation efficiency by selecting the most informative samples for annotation and model training. While most prior work has focused on selecting informative images for classification tasks, we investigate the more…

Active learning aims to improve the performance of task model by selecting the most informative samples with a limited budget. Unlike most recent works that focused on applying active learning for image classification, we propose an…

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem,…

In recent years, powerful data-driven deep-learning techniques have been developed and applied for automated catch registration. However, these methods are dependent on the labelled data, which is time-consuming, labour-intensive, expensive…

Documents are central to many business systems, and include forms, reports, contracts, invoices or purchase orders. The information in documents is typically in natural language, but can be organized in various layouts and formats. There…

We have seen significant leapfrog advancement in machine learning in recent decades. The central idea of machine learnability lies on constructing learning algorithms that learn from good data. The availability of more data being made…

Despite powering sensitive systems like autonomous vehicles, object detection remains fairly brittle in part due to annotation errors that plague most real-world training datasets. We propose ObjectLab, a straightforward algorithm to detect…

Curating an informative and representative dataset is essential for enhancing the performance of 2D object detectors. We present a novel active learning sampling strategy that addresses both the informativeness and diversity of the…

Active learning allows machine learning models to be trained using fewer labels while retaining similar performance to traditional supervised learning. An active learner selects the most informative data points, requests their labels, and…

To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance. Our…

Object detectors usually achieve promising results with the supervision of complete instance annotations. However, their performance is far from satisfactory with sparse instance annotations. Most existing methods for sparsely annotated…

Active learning algorithms automatically identify the most informative samples from large amounts of unlabeled data and tremendously reduce human annotation effort in inducing a machine learning model. In a conventional active learning…

Sketch recognition allows natural and efficient interaction in pen-based interfaces. A key obstacle to building accurate sketch recognizers has been the difficulty of creating large amounts of annotated training data. Several authors have…

LiDAR-based 3D object detection and semantic segmentation are critical tasks in 3D scene understanding. Traditional detection and segmentation methods supervise their models through bounding box labels and semantic mask labels. However,…

Deep neural network-based semantic segmentation generally requires large-scale cost extensive annotations for training to obtain better performance. To avoid pixel-wise segmentation annotations which are needed for most methods, recently…

When we can not assume a large amount of annotated data , active learning is a good strategy. It consists in learning a model on a small amount of annotated data (annotation budget) and in choosing the best set of points to annotate in…

To learn a reliable people counter from crowd images, head center annotations are normally required. Annotating head centers is however a laborious and tedious process in dense crowds. In this paper, we present an active learning framework…

Annotating the right set of data amongst all available data points is a key challenge in many machine learning applications. Batch active learning is a popular approach to address this, in which batches of unlabeled data points are selected…

Despite great progress in object detection, most existing methods work only on a limited set of object categories, due to the tremendous human effort needed for bounding-box annotations of training data. To alleviate the problem, recent…

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…