4 papers
Real-Time Object Detection Meets DINOv3
Shihua Huang, Yongjie Hou, Longfei Liu +2
Driven by the simple and effective Dense O2O, DEIM demonstrates faster convergence and enhanced performance. In this work, we extend it with DINOv3 features, resulting in DEIMv2. D…
SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements
Haiyang Xie, Xi Shen, Shihua Huang +2
Most visual models are designed for sRGB images, yet RAW data offers significant advantages for object detection by preserving sensor information before ISP processing. This enable…
DEIM: DETR with Improved Matching for Fast Convergence
Shihua Huang, Zhichao Lu, Xiaodong Cun +3
We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR). To m…
From COCO to COCO-FP: A Deep Dive into Background False Positives for COCO Detectors
Longfei Liu, Wen Guo, Shihua Huang +2
Reducing false positives is essential for enhancing object detector performance, as reflected in the mean Average Precision (mAP) metric. Although object detectors have achieved no…