Computer Vision Models

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.

Segment Anything 2 (SAM 2) is a real-time image and video segmentation model.

GPT-4o is OpenAI’s third major iteration of GPT-4 expanding on the capabilities of GPT-4 with Vision

PaliGemma is a vision language model (VLM) by Google that has multimodal capabilities.

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

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

The YOLOv8 pose estimation model allows you to detect keypoints in an image.

Segment Anything (SAM) is an image segmentation model developed by Meta Research, capable of doing zero-shot segmentation.

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

The state-of-the-art YOLOv8 model comes with support for instance segmentation tasks.

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

GPT-4.1 is a multimodal model developed by OpenAI that comes in three sizes: GPT-4.1, mini, and nano.

Claude 3.7 is a multimodal "hybrid reasoning" model developed by Anthropic.

Phi-4 Multimodal is a multimodal language model developed by Microsoft.

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

D-FINE is a real-time object detection model introduced in the paper " D-FINE: Redefine Regression Task of DETRs as Fine‑grained Distribution Refinement".

DEIM is a training framework for DETR models. The framework strives to enable "faster convergence and improved accuracy" in models.

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

SmolVLM2 is a multimodal image and video understanding model developed by engineers on the Hugging Face TB (Textbook) Research team.

Moondream 2 is the latest model in the Moondream series of “tiny vision language models”.

Gemma 3 is a multimodal language model developed by Google.

OpenAI o3-mini is a multimodal reasoning model developed by OpenAI.

Qwen2.5-VL is a multimodal vision-language model developed by the Qwen team at Alibaba Cloud.

PaliGemma-2 is a multimodal model developed by Google.

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

Florence-2 OCR is a subset of Florence-2 that can read characters in images.

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

Florence-2 is a lightweight vision-language model open-sourced by Microsoft under the MIT license.

You can use the set of PaliGemma weights trained on the OCRVQA dataset for performing OCR on images.

You can use the set of PaliGemma weights trained on the DocVQA dataset for asking questions about documents.

You can use the set of PaliGemma weights trained on the VQAv2 dataset for asking questions about the contents of images.

You can use the set of PaliGemma weights trained on the Screen2Words dataset for asking questions about website screenshots.

You can use the set of PaliGemma weights trained on the COCO Captions dataset for zero-shot image captioning.

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

MMOCR is an Optical Character Recognition model zoo implemented with the MMDetection package.

TrOCR is a Transformer-based OCR model developed by researchers from Microsoft Research.

Tesseract is a highly popular OCR engine and project, now primarily developed open-source.

Surya is a Python package designed for OCR on document layout analysis.

Gemini is a family of Large Multimodal Models (LMMs) developed by Google Deepmind focused specifically on multimodality.

ResNet-50 is a popular image classification model architecture.

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.

AltCLIP is a zero-shot image classification model.

RemoteCLIP is a zero-shot classification model for remote sensing.

BioCLIP is a Vision Foundation Model for the Tree of Life

MobileCLIP is an image embedding model developed by Apple and introduced in the "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training" paper

SigLIP is an image embedding model defined in the "Sigmoid Loss for Language Image Pre-Training" paper.

YOLO-NAS Pose is a keypoint detection model developed by Deci AI.

Grounded EdgeSAM is a combination of Grounding DINO, a zero-shot object detection model, and EdgeSAM, a fast zero-shot image segmentation model.

BakLLaVA is an LMM developed by LAION, Ontocord, and Skunkworks AI. BakLLaVA uses a Mistral 7B base augmented with the LLaVA 1.5 architecture.

CogVLM shows strong performance in Visual Question Answering (VQA) and other vision tasks.

Qwen-VL is an LMM developed by Alibaba Cloud. Qwen-VL accepts images, text, and bounding boxes as inputs. The model can output text and bounding boxes. Qwen-VL naturally supports English, Chinese, and multilingual conversation.

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

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

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.

GroundedSAM combines Grounding DINO with the Segment Anything Model to identify and segment objects in an image given text captions.

Use Grounding DINO, Segment Anything, and CLIP to label objects in images.

BLIPv2 is a multimodal model developed by Salesforce Research.

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

FastViT is a fast image classification model developed by Apple.

MetaCLIP is a zero-shot classification and embedding model developed by Meta AI.

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

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

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.

A simple, fully convolutional model for real-time instance segmentation

ByteTrack is a multi-object tracking computer vision algorithm.

FastSAM is an image segmentation model trained using 2% of the data in the Segment Anything Model SA-1B dataset.

Detic is an open source segmentation model developed by Meta Research and released in 2022.

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

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

An image classification model built using YOLOv8.

YOLOv7 Instance Segmentation lets you perform segmentation tasks with the YOLOv7 model.

OneFormer is a state-of-the-art multi-task image segmentation framework that is implemented using transformers.

A fast, simple convolutional neural network that gets the job done for many tasks, including classification.

YOLOX is a high-performance object detection model.

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

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

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

The Vision Transformer leverages powerful natural language processing embeddings (BERT) and applies them to images.

Mask RCNN is a convolutional neural network for instance segmentation.

SegFormer is a computer vision framework used in semantic segmentation tasks, implemented with transformers.

YOLOv5 Classification is a version of the YOLOv5 model used in single-label and multi-label image classification.

YOLOv5 Instance Segmentation is a version of YOLOv5 that can be used for instance segmentation tasks.