Shypd.aiThe largest open index of AI toolsOneNet is an open-source research project focused on end-to-end object detection, exploring label assignment methods. It provides models for COCO and CrowdHuman datasets, offering insights into improving one-stage object detection models.
Trending
About
OneNet is an open-source research project presented at ICML2021, focusing on advancing end-to-end object detection. It investigates the impact of different label assignment methods, particularly highlighting the importance of classification cost alongside position cost for effective end-to-end detection without requiring NMS post-processing. The project offers pre-trained models for both COCO and CrowdHuman datasets, including variants optimized for high accuracy (dcn) and easy deployment (nodcn). It provides detailed instructions for installation, training, evaluation, and visualization, built upon Detectron2 and DETR frameworks, making it a valuable resource for researchers and developers in computer vision.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
