dongkyunk/DOLG-pytorch
Unofficial PyTorch Implementation of "DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features"
This helps with finding specific instances of objects or landmarks within large collections of images. You provide a database of images, and it can efficiently find all images that contain a visually similar item to a query image. This is ideal for anyone managing vast image libraries, such as curators, archivists, or e-commerce platform managers.
135 stars. No commits in the last 6 months.
Use this if you need to quickly locate identical or near-identical objects, buildings, or natural landmarks across millions of images.
Not ideal if you're looking for images based on general categories (e.g., 'all pictures of dogs') rather than specific instances (e.g., 'all pictures of *this specific dog*').
Stars
135
Forks
16
Language
Python
License
MIT
Category
Last pushed
Dec 21, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dongkyunk/DOLG-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...