YOLOX and DAMO-YOLO
About YOLOX
Megvii-BaseDetection/YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Implements decoupled head architecture separating classification and localization branches, with dynamic label assignment during training to improve convergence. Provides multiple model scales from Nano (0.91M parameters) to X (99.1M parameters) optimized for various deployment scenarios, plus native PyTorch training with mixed-precision and distributed multi-machine support.
About DAMO-YOLO
tinyvision/DAMO-YOLO
DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work