DIOD: Self-Distillation Meets Object Discovery

S Kara, H Ammar, J Denize… - Proceedings of the …, 2024 - openaccess.thecvf.com
Instance segmentation demands substantial labeling resources. This has prompted
increased interest to explore the object discovery task as an unsupervised alternative. In …

Sparsely-Supervised Object Tracking

J Zheng, W Li, C Ma, X Yang - IEEE Transactions on Image …, 2024 - ieeexplore.ieee.org
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 …

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 …

Pseudo-Labeling and Contextual Curriculum Learning for Online Grasp Learning in Robotic Bin Picking

H Le, P Schillinger, M Gabriel, A Qualmann… - arXiv preprint arXiv …, 2024 - arxiv.org
The prevailing grasp prediction methods predominantly rely on offline learning, overlooking
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 …