Siamese and triplet networks with online pair/triplet mining in PyTorch

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

🎯 Task-oriented embedding tuning for BERT, CLIP, etc.

Implementation of triplet loss in TensorFlow

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Unsupervised Scalable Representation Learning for Multivariate Time Series: Experiments

Keras implementation of ‘’Deep Speaker: an End-to-End Neural Speaker Embedding System‘’ (speaker recognition)

A PyTorch implementation of the 'FaceNet' paper for training a facial recognition model with Triplet Loss using the glint360k dataset. A pre-trained model using Triplet Loss is available for download.

Person re-ID baseline with triplet loss

Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification

Deep Learning - one shot learning for speaker recognition using Filter Banks

A PyTorch-based toolkit for natural language processing

A generic triplet data loader for image classification problems,and a triplet loss net demo.

2020/2021 HKUST CSE FYP Masked Facial Recognition, developer: Sam Yuen, Alex Xie, Tony Cheng

Highly efficient PyTorch version of the Semi-hard Triplet loss ⚡️

A PyTorch implementation of CGD based on the paper "Combination of Multiple Global Descriptors for Image Retrieval"

This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods from a single image under variations in viewing angle, lighting, and common occlusions.

Image similarity using Triplet Loss

Complete Code for "Hard-Aware-Deeply-Cascaded-Embedding"

Determine whether a given video sequence has been manipulated or synthetically generated