2 papers
cs.CV2024
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…
cs.CV2024
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…