Object Detection

RF-DETR is a SOTA, real-time object detection model architecture developed by Roboflow and released under the Apache 2.0 license.

YOLOv12 is a state-of-the-art computer vision model you can use for detection, segmentation, and more.

YOLOv9 is an object detection model architecture released on February 21st, 2024.

YOLO-World is a zero-shot object detection model.

Grounding DINO is a zero-shot object detection model made by combining a Transformer-based DINO detector and grounded pre-training.

YOLOv8 is a state-of-the-art object detection and image segmentation model created by Ultralytics, the developers of YOLOv5.

The 4M model is a versatile multimodal Transformer model developed by EPFL and Apple, capable of handling a handful of vision and language tasks.

YOLOv10 is a real-time object detection model introduced in the paper "YOLOv10: Real-Time End-to-End Object Detection".

You can retrieve bounding boxes whose edges match an angled object by training an oriented bounding boxes object detection model, such as YOLOv8's Oriented Bounding Boxes model.

CoDet is an open vocabulary zero-shot object detection model.

LLaVA is an open source multimodal language model that you can use for visual question answering and has limited support for object detection.

YOLO-NAS is an object detection model developed by Deci that achieves SOTA performances compared to YOLOv5, v7, and v8.

Co-Deformable-DETR (Co-DETR) is an object detection model architecture introduced in the paper "DETRs with Collaborative Hybrid Assignments Training".

YOLOv7 is a state of the art object detection model.

MT-YOLOv6 is a YOLO based model released in 2022.

YOLOX is a high-performance object detection model.

YOLOS looks at patches of an image to to form "patch tokens", which are used in place of the traditional wordpiece tokens in NLP.

YOLOR (You Only Learn One Representation) is an object detection model that uses both implicit and explicit knowledge to make predictions.

The tiny and fast version of YOLOv4 - good for training and deployment on limited compute resources, and getting a feel for your dataset

Detection Transformer (DETR) is an end-to-end object detection model implemented using the Transformer architecture.

YOLOv5-OBB is a variant of YOLOv5 that supports oriented bounding boxes. This model is designed to yield predictions that better fit objects that are positioned at an angle.

A very fast and easy to use PyTorch model that achieves state of the art (or near state of the art) results.

EfficientDet achieves the best performance in the fewest training epochs among object detection model architectures, making it a highly scalable architecture especially when operating with limited compute.

A scalable, state of the art object detection model, implemented here within the TensorFlow 2 Object Detection API.

Though it is no longer the most accurate object detection algorithm, YOLO v3 is still a very good choice when you need real-time detection while maintaining excellent accuracy. PyTorch version.

This architecture provides good realtime results on limited compute. It's designed to run in realtime (30 frames per second) even on mobile devices.

YOLOE is a new object detection and segmentation model developed by the creators of YOLOv10.

YOLO11 is a computer vision model that you can use for object detection, segmentation, and classification.

VLPart, developed by Meta Research, is an object detection and segmentation model that works with an open vocabulary

GPT-4 with Vision is a multimodal language model developed by OpenAI.

Grounding DINO is a state-of-the-art zero-shot object detection model, developed by IDEA Research.

OWL-ViT is a transformer-based object detection model developed by Google Research.

OWLv2 is a transformer-based object detection model developed by Google Research. OWLv2 is the successor to OWL ViT.

Kosmos-2 is a multimodal language model capable of object detection and grounding text in images.

L2CS-Net is a gaze estimation model that enables you to calculate where someone is looking and in what direction someone is looking.

DocTR is an Optical Character Recognition tool powered by deep learning.

DINOv2 is a self-supervised method for training computer vision models developed by Meta Research and released in April 2023.

RTMDet is an efficient real-time object detector, with self-reported metrics outperforming the YOLO series. It achieves 52.8% AP on COCO with 300+ FPS on an NVIDIA 3090 GPU, making it one of the fastest and most accurate object detectors available as of writing this post.

ByteTrack is a multi-object tracking computer vision algorithm.

Scaled YOLOv4 is an extension of the YOLOv4 research implemented in the YOLOv5 PyTorch framework.

YOLOv4 has emerged as the best real time object detection model. YOLOv4 carries forward many of the research contributions of the YOLO family of models along with new modeling and data augmentation techniques. This implementation is in Darknet.

One of the most accurate object detection algorithms but requires a lot of power at inference time. A good choice if you can do processing asynchronously on a server.

Though it is no longer the most accurate object detection algorithm, YOLO v3 is still a very good choice when you need real-time detection while maintaining excellent accuracy. Keras implementation.

YOLOv4 has emerged as the best real time object detection model. YOLOv4 carries forward many of the research contributions of the YOLO family of models along with new modeling and data augmentation techniques. This implementation is in PyTorch.

Detectron2 is model zoo of it's own for computer vision models written in PyTorch.