Active teacher for semi-supervised object detection
In this paper, we study teacher-student learning from the perspective of data initialization
and propose a novel algorithm called Active Teacher for semi-supervised object detection …
and propose a novel algorithm called Active Teacher for semi-supervised object detection …
Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning
The capability of the traditional semi-supervised learning (SSL) methods is far from real-
world application due to severely biased pseudo-labels caused by (1) class imbalance and …
world application due to severely biased pseudo-labels caused by (1) class imbalance and …
Labor: Labeling only if required for domain adaptive semantic segmentation
Abstract Unsupervised Domain Adaptation (UDA) for semantic segmentation has been
actively studied to mitigate the domain gap between label-rich source data and unlabeled …
actively studied to mitigate the domain gap between label-rich source data and unlabeled …
Pt4al: Using self-supervised pretext tasks for active learning
Labeling a large set of data is expensive. Active learning aims to tackle this problem by
asking to annotate only the most informative data from the unlabeled set. We propose a …
asking to annotate only the most informative data from the unlabeled set. We propose a …
A novel anomaly detection approach based on ensemble semi-supervised active learning (ADESSA)
Z Niu, W Guo, J Xue, Y Wang, Z Kong, L Huang - Computers & Security, 2023 - Elsevier
As an industrial infrastructure, the safety and reliability of the Cyber-Physical System
requires the effective anomaly detection. However, the existing detection methods have …
requires the effective anomaly detection. However, the existing detection methods have …
[HTML][HTML] A multimodal auxiliary classification system for osteosarcoma histopathological images based on deep active learning
F Gou, J Liu, J Zhu, J Wu - Healthcare, 2022 - mdpi.com
Histopathological examination is an important criterion in the clinical diagnosis of
osteosarcoma. With the improvement of hardware technology and computing power …
osteosarcoma. With the improvement of hardware technology and computing power …
Unsupervised selective labeling for more effective semi-supervised learning
Given an unlabeled dataset and an annotation budget, we study how to selectively label a
fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled …
fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled …
Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery
The exploitation of visible spectrum datasets has led deep networks to show remarkable
success. However, real-world tasks include low-lighting conditions which arise performance …
success. However, real-world tasks include low-lighting conditions which arise performance …
Federated active learning (f-al): an efficient annotation strategy for federated learning
Federated learning (FL) has been intensively investigated in terms of communication
efficiency, privacy, and fairness. However, efficient annotation, which is a pain point in real …
efficiency, privacy, and fairness. However, efficient annotation, which is a pain point in real …
Towards inference efficient deep ensemble learning
Ensemble methods can deliver surprising performance gains but also bring significantly
higher computational costs, eg, can be up to 2048X in large-scale ensemble tasks …
higher computational costs, eg, can be up to 2048X in large-scale ensemble tasks …