Open-set object detector that by combines a Transformer-based detector DINO with grounded pre-training. It can detect arbitrary objects with human inputs such as category names or referring expressions. Useful for zero shot object detection tasks...
Yolo8 Object Detection
Ultralytics YOLOv8 is the latest version of the acclaimed real-time object detection and image segmentation model. YOLOv8 is built on cutting-edge advancements in deep learning and computer vision, offering unparalleled performance in terms of speed and accuracy...
Ultralytics YOLOv8 is the latest version of the acclaimed real-time object detection and image segmentation model. OLOv8 is built on cutting-edge advancements in deep learning and computer vision, offering unparalleled performance in terms of speed and accuracy. The YOLOv8 image classification model is designed to detect 1000 pre-defined classes in images in real-time...
YOLOv7 is the fastest and most accurate real-time object detection model for computer vision tasks. It was introduced to the YOLO family in July'22. YOLOv7 established a significant benchmark by taking its performance up a notch. The models are trained using the COCO dataset entirely.
YOLOv6: a single-stage object detection framework dedicated to industrial applications. OLOv6 Nano model has achieved an mAP of 35.6% on the COCO dataset. Also, it runs at more than 1200 FPS on an NVIDIA Tesla T4 GPU with a batch size of 32.
Detectron2 is Facebook AI Research's next-generation library that provides state-of-the-art detection and segmentation algorithms. It includes implementations for the following object detection algorithms: Mask R-CNN, RetinaNet, Faster R-CNN, RPN, Fast R-CNN, TensorMask, PointRend, DensePose.
SAM (Segment Anything Model) 2D & 3D
SAM (Segment Anything Model) was released by Meta. It is an AI model that can segment any object in an image or video with a single click. SAM is trained on a massive dataset of over 1 billion masks, which allows it to generalize to new types of objects and images. SAM has learned a general understanding of what objects are...