DIOD: Self-Distillation Meets Object Discovery
Instance segmentation demands substantial labeling resources. This has prompted
increased interest to explore the object discovery task as an unsupervised alternative. In …
increased interest to explore the object discovery task as an unsupervised alternative. In …
Sparsely-Supervised Object Tracking
Recent years have witnessed the incredible performance boost of data-driven deep visual
object trackers. Despite the success, these trackers require millions of sequential manual …
object trackers. Despite the success, these trackers require millions of sequential manual …
A Cooperative Training Framework for Underwater Object Detection on a Clearer View
G Chen, Z Mao, Q Tu, J Shen - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Underwater optical image object detection plays a crucial role in fields such as ocean
exploration. However, constructing a comprehensive annotated dataset for training is …
exploration. However, constructing a comprehensive annotated dataset for training is …
Pseudo-Labeling and Contextual Curriculum Learning for Online Grasp Learning in Robotic Bin Picking
The prevailing grasp prediction methods predominantly rely on offline learning, overlooking
the dynamic grasp learning that occurs during real-time adaptation to novel picking …
the dynamic grasp learning that occurs during real-time adaptation to novel picking …
Addressing Sparse Annotation: a Novel Semantic Energy Loss for Tumor Cell Detection from Histopathologic Images
Z Xu, XL Du, Y Kang, H Lv, M Li, W Yang… - 2023 IEEE …, 2023 - ieeexplore.ieee.org
Tumor cell detection plays a vital role in immunohistochemistry (IHC) quantitative analysis.
While recent remarkable developments in fully-supervised deep learning have greatly …
While recent remarkable developments in fully-supervised deep learning have greatly …