Hybrid Classification-Regression Adaptive Loss for Dense Object Detection

no code implementations • 30 Aug 2024 • Yanquan Huang, Liu Wei Zhen, Yun Hao, Mengyuan Zhang, Qingyao Wu, Zikun Deng, Xueming Liu, Hong Deng

For object detection detectors, enhancing model performance hinges on the ability to simultaneously consider inconsistencies across tasks and focus on difficult-to-train samples.

Classification Dense Object Detection +2