IvanAer/G-Universal-CLIP
4th place solution for the Google Universal Image Embedding Kaggle Challenge. Instance-Level Recognition workshop at ECCV 2022
This helps computer vision researchers and practitioners efficiently retrieve specific images from vast, unlabeled collections. It takes an image or text description as input and outputs relevant images, even if those images haven't been seen before. This tool is ideal for anyone working with large visual datasets who needs to find specific content without extensive manual labeling or setup.
No commits in the last 6 months.
Use this if you need to find specific images within a huge, diverse dataset using either another image or a text description, and you want to do this without extensive pre-labeling or fine-tuning.
Not ideal if your image retrieval needs are based on highly niche, abstract concepts that are poorly represented by general image and text embeddings.
Stars
43
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/IvanAer/G-Universal-CLIP"
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...
deepmancer/clip-object-detection
Zero-shot object detection with CLIP, utilizing Faster R-CNN for region proposals.
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...
joanrod/ocr-vqgan
OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in...