Showing cs.CVShow all
3 papers · 1 filter
cs.CV2024
Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning
Hoà ng-Ãn Lê, Paul Berg, Minh-Tan Pham
Object detection and semantic segmentation are both scene understanding tasks yet they differ in data structure and information level. Object detection requires box coordinates for…
cs.CV2024
Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasets
Hoà ng-Ãn Lê, Minh-Tan Pham
Partial multi-task learning where training examples are annotated for one of the target tasks is a promising idea in remote sensing as it allows combining datasets annotated for di…
cs.CV2024
Leveraging feature communication in federated learning for remote sensing image classification
Anh-Kiet Duong, Hoà ng-Ãn Lê, Minh-Tan Pham
In the realm of Federated Learning (FL) applied to remote sensing image classification, this study introduces and assesses several innovative communication strategies. Our explorat…