leeesangwon / Pytorch Image Retrieval
Licence: mit
A PyTorch framework for an image retrieval task including implementation of N-pair Loss (NIPS 2016) and Angular Loss (ICCV 2017).
Stars: ✭ 203
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Pytorch Image Retrieval
Batch Dropblock Network
Official source code of "Batch DropBlock Network for Person Re-identification and Beyond" (ICCV 2019)
Stars: ✭ 304 (+49.75%)
Mutual labels: image-retrieval, metric-learning
Revisiting deep metric learning pytorch
(ICML 2020) This repo contains code for our paper "Revisiting Training Strategies and Generalization Performance in Deep Metric Learning" (https://arxiv.org/abs/2002.08473) to facilitate consistent research in the field of Deep Metric Learning.
Stars: ✭ 172 (-15.27%)
Mutual labels: image-retrieval, metric-learning
Person reid baseline pytorch
Pytorch ReID: A tiny, friendly, strong pytorch implement of object re-identification baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
Stars: ✭ 2,963 (+1359.61%)
Mutual labels: image-retrieval, metric-learning
GPQ
Generalized Product Quantization Network For Semi-supervised Image Retrieval - CVPR 2020
Stars: ✭ 60 (-70.44%)
Mutual labels: metric-learning, image-retrieval
Powerful Benchmarker
A PyTorch library for benchmarking deep metric learning. It's powerful.
Stars: ✭ 272 (+33.99%)
Mutual labels: image-retrieval, metric-learning
symmetrical-synthesis
Official Tensorflow implementation of "Symmetrical Synthesis for Deep Metric Learning" (AAAI 2020)
Stars: ✭ 67 (-67%)
Mutual labels: metric-learning, image-retrieval
proxy-synthesis
Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)
Stars: ✭ 30 (-85.22%)
Mutual labels: metric-learning, image-retrieval
Pytorch Metric Learning
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
Stars: ✭ 3,936 (+1838.92%)
Mutual labels: image-retrieval, metric-learning
Hardnet
Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"
Stars: ✭ 350 (+72.41%)
Mutual labels: image-retrieval, metric-learning
Kapture
kapture is a file format as well as a set of tools for manipulating datasets, and in particular Visual Localization and Structure from Motion data.
Stars: ✭ 128 (-36.95%)
Mutual labels: image-retrieval
Deep metric learning
Deep metric learning methods implemented in Chainer
Stars: ✭ 153 (-24.63%)
Mutual labels: metric-learning
Hypertag
Knowledge Management for Humans using Machine Learning & Tags
Stars: ✭ 116 (-42.86%)
Mutual labels: image-retrieval
Openibl
[ECCV-2020 (spotlight)] Self-supervising Fine-grained Region Similarities for Large-scale Image Localization. 🌏 PyTorch open-source toolbox for image-based localization (place recognition).
Stars: ✭ 128 (-36.95%)
Mutual labels: image-retrieval
Person Reid Triplet Loss
Person re-ID baseline with triplet loss
Stars: ✭ 165 (-18.72%)
Mutual labels: image-retrieval
Dml cross entropy
Code for the paper "A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses" (ECCV 2020 - Spotlight)
Stars: ✭ 117 (-42.36%)
Mutual labels: metric-learning
Proxy Anchor Cvpr2020
Official PyTorch Implementation of Proxy Anchor Loss for Deep Metric Learning, CVPR 2020
Stars: ✭ 188 (-7.39%)
Mutual labels: image-retrieval
Declutr
The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to open an issue if you run into any trouble!
Stars: ✭ 111 (-45.32%)
Mutual labels: metric-learning
Pytorch deephash
Pytorch implementation of Deep Learning of Binary Hash Codes for Fast Image Retrieval, CVPRW 2015
Stars: ✭ 148 (-27.09%)
Mutual labels: image-retrieval
Manifold Diffusion
Diffusion on manifolds for image retrieval
Stars: ✭ 102 (-49.75%)
Mutual labels: image-retrieval
Revisitop
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
Stars: ✭ 147 (-27.59%)
Mutual labels: image-retrieval
PyTorch Image Retrieval
A PyTorch framework for an image retrieval task including implementation of N-pair Loss (NIPS 2016) and Angular Loss (ICCV 2017).
Loss functions
We implemented loss functions to train the network for image retrieval.
Batch sampler for the loss function borrowed from here.
- N-pair Loss (NIPS 2016): Sohn, Kihyuk. "Improved Deep Metric Learning with Multi-class N-pair Loss Objective," Advances in Neural Information Processing Systems. 2016.
- Angular Loss (ICCV 2017): Wang, Jian. "Deep Metric Learning with Angular Loss," ICCV, 2017
Self-attention module
We attached the self-attention module of the Self-Attention GAN to conventional classification networks (e.g. DenseNet, ResNet, or SENet).
Implementation of the module borrowed from here.
Data augmentation
We adopted data augmentation techniques used in Single Shot MultiBox Detector.
Post processing
We utilized the following post-processing techniques in the inference phase.
- Moving the origin of the feature space to the center of the feature vectors
- L2-normalization
- Average query expansion
- Database-side feature augmentation
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].