Real-time and accurate open-vocabulary end-to-end object detection

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

Official implementation of OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion

Use Florence 2 to auto-label data for use in training fine-tuned object detection models.

Image Instance Segmentation - Zero Shot - OpenAI's CLIP + Meta's SAM

[WACV 2025] Official code for our paper "Enhancing Novel Object Detection via Cooperative Foundational Models"

Creating multimodal multitask models

[CVPR2024 Highlight] Official repository of the paper "The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding."

使用onnxruntime部署GroundingDINO开放世界目标检测，包含C++和Python两个版本的程序

A curated list of papers, datasets and resources pertaining to zero-shot object detection.

Low-latency ONNX and TensorRT based zero-shot classification and detection with contrastive language-image pre-training based prompts

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

Resolving semantic confusions for improved zero-shot detection (BMVC 2022)

Use PaliGemma to auto-label data for use in training fine-tuned vision models.

EfficientSAM + YOLO World base model for use with Autodistill.

Zero-shot object detection with CLIP, utilizing Faster R-CNN for region proposals.

OWLv2 base model for use with Autodistill.

YOLO World base module for use with Autodistill.