Active teacher for semi-supervised object detection

P Mi, J Lin, Y Zhou, Y Shen, G Luo… - Proceedings of the …, 2022 - openaccess.thecvf.com
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 …

Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning

Y Oh, DJ Kim, IS Kweon - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
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 …

Labor: Labeling only if required for domain adaptive semantic segmentation

I Shin, DJ Kim, JW Cho, S Woo… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract Unsupervised Domain Adaptation (UDA) for semantic segmentation has been
actively studied to mitigate the domain gap between label-rich source data and unlabeled …

Pt4al: Using self-supervised pretext tasks for active learning

JSK Yi, M Seo, J Park, DG Choi - European Conference on Computer …, 2022 - Springer
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 …

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 …

[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 …

Unsupervised selective labeling for more effective semi-supervised learning

X Wang, L Lian, SX Yu - European Conference on Computer Vision, 2022 - Springer
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 …

Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery

B Ustun, AK Kaya, EC Ayerden… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Federated active learning (f-al): an efficient annotation strategy for federated learning

JH Ahn, Y Ma, S Park, C You - IEEE Access, 2024 - ieeexplore.ieee.org
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 …

Towards inference efficient deep ensemble learning

Z Li, K Ren, Y Yang, X Jiang, Y Yang, D Li - Proceedings of the AAAI …, 2023 - ojs.aaai.org
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 …