PyTorch Implementation for Deep Metric Learning Pipelines

(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.

Comparison of famous convolutional neural network models

Official MXNet implementation of "Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning" (CVPR 2020)

Official Tensorflow implementation of "Symmetrical Synthesis for Deep Metric Learning" (AAAI 2020)

(ICCV 2019) This repo contains code for "MIC: Mining Interclass Characteristics for Improved Metric Learning", which proposes an auxiliary training task to explain away intra-class variations.

(CVPR 2020) This repo contains code for "PADS: Policy-Adapted Sampling for Visual Similarity Learning", which proposes learnable triplet mining with Reinforcement Learning.

Official PyTorch(MMCV) implementation of “Adversarial AutoMixup” (ICLR 2024 spotlight)

(ICML 2021) Implementation for S2SD - Simultaneous Similarity-based Self-Distillation for Deep Metric Learning. Paper Link: https://arxiv.org/abs/2009.08348

(ECCV 2020) This repo contains code for "DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning" (https://arxiv.org/abs/2004.13458), which extends vanilla DML with auxiliary and self-supervised features.

Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)

Hardness-Aware Deep Metric Learning (CVPR2019) in pytorch

Implementation and Benchmark Splits to study Out-of-Distribution Generalization in Deep Metric Learning.

Official PyTorch implementation of "Learning with Memory-based Virtual Classes for Deep Metric Learning" (ICCV 2021)

Image Classification Training Framework for Network Distillation

Project that detects the model of a car, between 1 and 196 models ( the 196 modelss of Stanford car file), that appears in a photograph with a success rate of more than 70% (using a test file that has not been involved in the training as a valid or training file, "unseen data") and can be implemented on a personal computer.