Detection Task
Object detection, a core computer vision task, aims to identify and locate objects within images or videos. Current research focuses on improving accuracy and efficiency across diverse domains, employing architectures like YOLO (various versions), DETR, and transformers, often enhanced with techniques such as knowledge distillation and data augmentation (including synthetic data generation). These advancements are crucial for applications ranging from autonomous driving and robotics to medical image analysis and resource management in industries like food processing, significantly impacting various scientific fields and practical applications.
Papers
Efficient Transformer-based 3D Object Detection with Dynamic Token Halting
Mao Ye, Gregory P. Meyer, Yuning Chai, Qiang Liu
Smooth and Stepwise Self-Distillation for Object Detection
Jieren Deng, Xin Zhou, Hao Tian, Zhihong Pan, Derek Aguiar
ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
Ying Zeng, Yushi Chen, Xue Yang, Qingyun Li, Junchi Yan