# COCO Dataset

YOLOv10x is the latest version of the YOLO series, focusing on real-time end-to-end object detection, offering higher detection accuracy and faster inference speed.

YOLOv10 is a real-time end-to-end object detection model developed by the Tsinghua University team, based on the latest improved version of the YOLO series.

YOLOv10 is a real-time end-to-end object detection model developed by the Tsinghua University team, representing the latest improvement in the YOLO series.

YOLOv10 is a real-time end-to-end object detection model proposed by Tsinghua University, known for its efficiency and accuracy.

YOLOv10 is a real-time object detection model that achieves efficient and overhead-free object detection by eliminating post-processing steps such as Non-Maximum Suppression (NMS).

Mask2Former is a Transformer-based unified image segmentation model supporting instance segmentation, semantic segmentation, and panoptic segmentation tasks, utilizing masked attention mechanism to enhance performance

A small-scale version of Mask2Former based on Swin backbone network, optimized for panoptic segmentation tasks on the COCO dataset

A large-scale version of Mask2Former based on the Swin backbone network, specifically trained for panoptic segmentation tasks on the COCO dataset

The Mask2Former model based on the Swin backbone network, trained on the COCO panoptic segmentation dataset, adopts a unified paradigm to handle instance segmentation, semantic segmentation, and panoptic segmentation tasks.

Mask2Former is a Transformer-based unified image segmentation model, utilizing a Swin-Large backbone and fine-tuned on the COCO dataset, specializing in instance segmentation tasks.

A unified single Transformer architecture for image segmentation, supporting three major tasks: semantic segmentation, instance segmentation, and panoptic segmentation

A small-sized YOLOS model fine-tuned on the COCO 2017 object detection dataset, utilizing Vision Transformer architecture for efficient object detection

A YOLOS model fine-tuned on the COCO 2017 object detection dataset, utilizing a Vision Transformer architecture, suitable for object detection tasks.

A vision Transformer (ViT)-based object detection model trained with DETR loss function, achieving excellent performance on the COCO dataset.

YOLOS model fine-tuned on the COCO 2017 object detection dataset, utilizing Vision Transformer architecture for efficient object detection.

DETR is an end-to-end object detection model based on Transformer architecture, using ResNet-50 as the backbone network, trained on the COCO dataset, and supports object detection and panoptic segmentation tasks.

Large-scale MaskFormer model based on Swin backbone network, unifying instance/semantic/panoptic segmentation tasks

A small MaskFormer model based on the Swin backbone network, trained on the COCO dataset for panoptic segmentation tasks.

A panoptic segmentation model trained on the COCO dataset, using a unified paradigm to handle instance/semantic/panoptic segmentation tasks

A panoptic segmentation model based on the Swin backbone network, trained on the COCO dataset, unifying instance/semantic/panoptic segmentation tasks