Elias Ramzi's starred repositories
pytorch-metric-learning
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
releasing-research-code
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
deepcluster
Deep Clustering for Unsupervised Learning of Visual Features
texture-vs-shape
Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)
Deep-Metric-Learning-Baselines
PyTorch Implementation for Deep Metric Learning Pipelines
Stylized-ImageNet
Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)
powerful-benchmarker
A library for ML benchmarking. It's powerful.
blackbox-backprop
Torch modules that wrap blackbox combinatorial solvers according to the method presented in "Differentiating Blackbox Combinatorial Solvers"
research-xbm
XBM: Cross-Batch Memory for Embedding Learning
semantic-embeddings
Hierarchy-based Image Embeddings for Semantic 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)
FastAP-metric-learning
Code for CVPR 2019 paper "Deep Metric Learning to Rank"
RecallatK_surrogate
Code for Recall@k Surrogate Loss with Large Batches and Similarity Mixup, CVPR 2022.
proxynca_pp
The implementation of ProxyNCA++.
multilabel-deep-metric
Adapted Triplet loss based metric learning to learn a metric for multilabel points, such that samples with maximum overlap in label sets are close.
fullbatchtraining
Training vision models with full-batch gradient descent and regularization