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

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Torchreid: Deep learning person re-identification in PyTorch.

⛹️ Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

[IJCV 2022] Bridging Composite and Real: Towards End-to-end Deep Image Matting

Deep InfoMax (DIM), or "Learning Deep Representations by Mutual Information Estimation and Maximization"

Unsupervised Feature Learning via Non-parametric Instance Discrimination

Deep Learning for Person Re-identification: A Survey and Outlook

Pytorch Code for Cross-Modality Person Re-Identification (Visible Thermal/Infrared Re-ID)

PCB of paper: Beyond Part Models: Person Retrieval with Refined Part Pooling, using Pytorch

See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks (CVPR19)

A collection of state-of-the-art face super-resolution/hallucination methods

A Bottom-Up Clustering Approach to Unsupervised Person Re-identification, AAAI 2019 (Oral)

Code for Unsupervised Embedding Learning via Invariant and Spreading Instance Feature

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval (CVPR 2023)

PyTorch Implementation of `No Fuss Distance Metric Learning using Proxies`.

GOM：New Metric for Re-identification. 👉GOM explicitly balances the effect of performing retrieval and verification into a single unified metric.

Demo code for visible thermal (cross-modality) person re-identification

[CVPR 2019] Pytorch codes for Multi-adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection

Pytorch Code of DDAG for Visible-Infrared Person Re-Identification (ECCV20)

Metric learning models in PyTorch with results on CUB2011, CARS196, Stanford Online Products

Project page for Heated-up Softmax Embedding

code for Scale-Adaptive Low Resolution Person Re-identification

Pytorch implementation of 'Improving Self-supervised Lightweight Model Learning via Hard-aware Metric Distillation. In ECCV 2022'