Recent advances in complementary label learning
Abstract Complementary Label Learning (CLL), a crucial aspect of weakly supervised
learning, has seen significant theoretical and practical advancements. However, a …
learning, has seen significant theoretical and practical advancements. However, a …
Tackling biased complementary label learning with large margin
Y You, J Huang, Q Tong, B Wang - Information Sciences, 2025 - Elsevier
Abstract Complementary Label Learning (CLL) is a typical weakly supervised learning
protocol, where each instance is associated with one complementary label to specify a class …
protocol, where each instance is associated with one complementary label to specify a class …
Dual Dynamic Threshold Adjustment Strategy
Loss functions and sample mining strategies are essential components in deep metric
learning algorithms. However, the existing loss function or mining strategy often necessitates …
learning algorithms. However, the existing loss function or mining strategy often necessitates …
Relating CNN-Transformer Fusion Network for Change Detection
While deep learning, particularly convolutional neural networks (CNNs), has revolutionized
remote sensing (RS) change detection (CD), existing approaches often miss crucial features …
remote sensing (RS) change detection (CD), existing approaches often miss crucial features …
[HTML][HTML] SAR ATR 中标签噪声不确定性建模与纠正
于跃, 王琛, 师君, 陶重犇, 李良, 唐欣欣, 周黎明… - 雷达学报, 2024 - radars.ac.cn
深度监督学习在合成孔径雷达自动目标识别任务中的成功依赖于大量标签样本. 但是,
在大规模数据集中经常存在错误(噪声) 标签, 很大程度降低网络训练效果 …
在大规模数据集中经常存在错误(噪声) 标签, 很大程度降低网络训练效果 …
Group benefits instance for data purification
Z Cai, C Zhang, D Huang, Y Chen, X Guan… - Computers and Electrical …, 2024 - Elsevier
Manually annotating datasets for training deep models is very labor-intensive and time-
consuming. To overcome such inferiority, directly leveraging web images to conduct training …
consuming. To overcome such inferiority, directly leveraging web images to conduct training …
Dual Dynamic Threshold Adjustment Strategy for Deep Metric Learning
Loss functions and sample mining strategies are essential components in deep metric
learning algorithms. However, the existing loss function or mining strategy often necessitate …
learning algorithms. However, the existing loss function or mining strategy often necessitate …
Foster Adaptivity and Balance in Learning with Noisy Labels
Label noise is ubiquitous in real-world scenarios, posing a practical challenge to supervised
models due to its effect in hurting the generalization performance of deep neural networks …
models due to its effect in hurting the generalization performance of deep neural networks …
Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation
Though adversarial erasing has prevailed in weakly supervised semantic segmentation to
help activate integral object regions, existing approaches still suffer from the dilemma of …
help activate integral object regions, existing approaches still suffer from the dilemma of …
A Light-weight Transformer-based Self-supervised Matching Network for Heterogeneous Images
W Zhang, T Li, Y Zhang, G Pei, X Jiang… - arXiv preprint arXiv …, 2024 - arxiv.org
Matching visible and near-infrared (NIR) images remains a significant challenge in remote
sensing image fusion. The nonlinear radiometric differences between heterogeneous …
sensing image fusion. The nonlinear radiometric differences between heterogeneous …