ShirAmir/dino-vit-features
Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".
This project helps anyone working with images to automatically identify common objects or parts across a collection of photos, or to find corresponding points between two related images. You provide sets of images, and it outputs segmented images highlighting shared elements or precise point matches. It's ideal for computer vision researchers, image analysts, or quality control inspectors.
464 stars. No commits in the last 6 months.
Use this if you need to automatically segment common objects within multiple images, partition those objects into shared parts, or find precise matching points between image pairs.
Not ideal if you're looking for a general-purpose image labeling tool or if your primary goal is to classify entire images.
Stars
464
Forks
59
Language
Python
License
MIT
Category
Last pushed
Sep 09, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ShirAmir/dino-vit-features"
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.
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
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...