This is an differentiable pytorch implementation of SIFT patch descriptor.

Last update: Dec 24, 2022

Overview

This is an differentiable pytorch implementation of SIFT patch descriptor. It is very slow for describing one patch, but quite fast for batch. It can be used for descriptop-based learning shape of affine feature.

UPD 08/2019 : pytorch-sift is added to kornia and available by kornia.features.SIFTDescriptor

There are different implementations of the SIFT on the web. I tried to match Michal Perdoch implementation, which gives high quality features for image retrieval CVPR2009. However, on planar datasets, it is inferior to vlfeat implementation. The main difference is gaussian weighting window parameters, so I have made a vlfeat-like version too. MP version weights patch center much more (see image below, left) and additionally crops everything outside the circular region. Right is vlfeat version

descriptor_mp_mode = SIFTNet(patch_size = 65,
                        sigma_type= 'hesamp',
                        masktype='CircularGauss')

descriptor_vlfeat_mode = SIFTNet(patch_size = 65,
                        sigma_type= 'vlfeat',
                        masktype='Gauss')

Results:

OPENCV-SIFT - mAP 
   Easy     Hard      Tough     mean
-------  -------  ---------  -------
0.47788  0.20997  0.0967711  0.26154

VLFeat-SIFT - mAP 
    Easy      Hard      Tough      mean
--------  --------  ---------  --------
0.466584  0.203966  0.0935743  0.254708

PYTORCH-SIFT-VLFEAT-65 - mAP 
    Easy      Hard      Tough      mean
--------  --------  ---------  --------
0.472563  0.202458  0.0910371  0.255353

NUMPY-SIFT-VLFEAT-65 - mAP 
    Easy      Hard      Tough      mean
--------  --------  ---------  --------
0.449431  0.197918  0.0905395  0.245963

PYTORCH-SIFT-MP-65 - mAP 
    Easy      Hard      Tough      mean
--------  --------  ---------  --------
0.430887  0.184834  0.0832707  0.232997

NUMPY-SIFT-MP-65 - mAP 
    Easy     Hard      Tough      mean
--------  -------  ---------  --------
0.417296  0.18114  0.0820582  0.226832

Speed:

0.00246 s per 65x65 patch - numpy SIFT
0.00028 s per 65x65 patch - C++ SIFT
0.00074 s per 65x65 patch - CPU, 256 patches per batch
0.00038 s per 65x65 patch - GPU (GM940, mobile), 256 patches per batch
0.00038 s per 65x65 patch - GPU (GM940, mobile), 256 patches per batch

If you use this code for academic purposes, please cite the following paper:

@InProceedings{AffNet2018,
    title = {Repeatability Is Not Enough: Learning Affine Regions via Discriminability},
    author = {Dmytro Mishkin, Filip Radenovic, Jiri Matas},
    booktitle = {Proceedings of ECCV},
    year = 2018,
    month = sep
}

This is an differentiable pytorch implementation of SIFT patch descriptor.

Related tags

Overview

Owner

Dmytro Mishkin

pip install antialiased-cnns to improve stability and accuracy

ocaml-torch provides some ocaml bindings for the PyTorch tensor library.

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

Implements pytorch code for the Accelerated SGD algorithm.

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

TorchSSL: A PyTorch-based Toolbox for Semi-Supervised Learning

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

A PyTorch implementation of L-BFGS.

Use Jax functions in Pytorch with DLPack

A code copied from google-research which named motion-imitation was rewrited with PyTorch

A tiny package to compare two neural networks in PyTorch

A simplified framework and utilities for PyTorch

A Pytorch Implementation for Compact Bilinear Pooling.

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

Code for paper "Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking"

Fast Discounted Cumulative Sums in PyTorch

The goal of this library is to generate more helpful exception messages for numpy/pytorch matrix algebra expressions.

You like pytorch? You like micrograd? You love tinygrad! ❤️

Official implementations of EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis.

PyTorch extensions for fast R&D prototyping and Kaggle farming