Related papers: Annotation Cost-Efficient Active Learning for Deep…

Active learning (AL) is a promising ML paradigm that has the potential to parse through large unlabeled data and help reduce annotation cost in domains where labeling data can be prohibitive. Recently proposed neural network based AL…

With the development of deep learning, Deep Metric Learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax loss in the training process often bring large intra-class variations, and feature…

Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality,…

Deep Learning for medical imaging faces challenges in adapting and generalizing to new contexts. Additionally, it often lacks sufficient labeled data for specific tasks requiring significant annotation effort. Continual Learning (CL)…

Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in…

Aging civil infrastructures are closely monitored by engineers for damage and critical defects. As the manual inspection of such large structures is costly and time-consuming, we are working towards fully automating the visual inspections…

We propose a new batch mode active learning algorithm designed for neural networks and large query batch sizes. The method, Discriminative Active Learning (DAL), poses active learning as a binary classification task, attempting to choose…

Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PDML) in this paper. PDML does not require dense annotated…

Deep Active Learning (DAL) aims to reduce labeling costs in neural-network training by prioritizing the most informative unlabeled samples for annotation. Beyond selecting which samples to label, several DAL approaches further enhance data…

Drone-view Geo-Localization (DVGL) aims to achieve accurate localization of drones by retrieving the most relevant GPS-tagged satellite images. However, most existing methods heavily rely on strictly pre-paired drone-satellite images for…

Label assignment is a crucial process in object detection, which significantly influences the detection performance by determining positive or negative samples during training process. However, existing label assignment strategies barely…

Deep learning is advancing EEG processing for automated epileptic seizure detection and onset zone localization, yet its performance relies heavily on high-quality annotated training data. However, scalp EEG is susceptible to high noise…

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…

Requirement of large annotated datasets restrict the use of deep convolutional neural networks (CNNs) for many practical applications. The problem can be mitigated by using active learning (AL) techniques which, under a given annotation…

Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyper-parameters. In contrast to…

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each…

Active learning (AL) attempts to maximize the performance gain of the model by marking the fewest samples. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize massive parameters, so that the model…

While deep learning is a powerful tool for natural language processing (NLP) problems, successful solutions to these problems rely heavily on large amounts of annotated samples. However, manually annotating data is expensive and…

Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarce text classification. However, existing CSAL methods…

Due to the publicly available thematic maps and crowd-sourced data, remote sensing (RS) image annotations can be gathered at zero cost for training deep neural networks (DNNs). However, such annotation sources may increase the risk of…