htdt/hyp_metric
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning | Official repository
This project helps machine learning engineers and researchers improve how computer vision models recognize similar images. It takes a collection of images and outputs a more refined way for the model to understand the visual relationships between them, especially when distinctions are subtle. This is for professionals building advanced image recognition systems, such as for fine-grained product classification or identifying specific animal species.
209 stars. No commits in the last 6 months.
Use this if you need to train or evaluate image recognition models to accurately group or distinguish visually similar items within large datasets, achieving state-of-the-art results in metric learning.
Not ideal if you are looking for a plug-and-play solution for general image classification without diving into advanced model training and evaluation techniques.
Stars
209
Forks
23
Language
Python
License
MIT
Category
Last pushed
Jun 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/htdt/hyp_metric"
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...