deepmancer/clip-object-detection
Zero-shot object detection with CLIP, utilizing Faster R-CNN for region proposals.
This helps you automatically find specific objects in images without needing to train a custom model. You provide an image and a text description of what you're looking for, and it returns the image with the identified objects highlighted. It's ideal for anyone who needs to quickly pinpoint items in visual content without extensive setup.
No commits in the last 6 months.
Use this if you need to rapidly detect various objects in images using simple text descriptions, without the time or resources for custom model training.
Not ideal if you require extremely precise object boundaries or need to detect objects that are very obscure or conceptually distant from common visual representations.
Stars
42
Forks
8
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/deepmancer/clip-object-detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OBA-Research/VAAS
VAAS is an inference-first, research-driven library for image integrity analysis. It integrates...
ABaldrati/CLIP4Cir
[ACM TOMM 2023] - Composed Image Retrieval using Contrastive Learning and Task-oriented...
kyegomez/CLIPQ
A simple implementation of a CLIP that splits up an image into quandrants and then gets the...
IvanAer/G-Universal-CLIP
4th place solution for the Google Universal Image Embedding Kaggle Challenge. Instance-Level...
joanrod/ocr-vqgan
OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in...