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 (+309.52%)
MvgcnMulti-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson's Disease (AMIA 2018)
Stars: ✭ 81 (+92.86%)
CVPR2020 PADS(CVPR 2020) This repo contains code for "PADS: Policy-Adapted Sampling for Visual Similarity Learning", which proposes learnable triplet mining with Reinforcement Learning.
Stars: ✭ 57 (+35.71%)
AmsoftmaxA simple yet effective loss function for face verification.
Stars: ✭ 443 (+954.76%)
DeclutrThe 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 (+164.29%)
LearningToCompare-TensorflowTensorflow implementation for paper: Learning to Compare: Relation Network for Few-Shot Learning.
Stars: ✭ 17 (-59.52%)
Hcn Prototypeloss PytorchHierarchical Co-occurrence Network with Prototype Loss for Few-shot Learning (PyTorch)
Stars: ✭ 17 (-59.52%)
simple-cnapsSource codes for "Improved Few-Shot Visual Classification" (CVPR 2020), "Enhancing Few-Shot Image Classification with Unlabelled Examples" (WACV 2022), and "Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning" (Neural Networks 2022 - in submission)
Stars: ✭ 88 (+109.52%)
Voxceleb trainerIn defence of metric learning for speaker recognition
Stars: ✭ 316 (+652.38%)
GeDMLGeneralized Deep Metric Learning.
Stars: ✭ 30 (-28.57%)
Magnetloss PytorchPyTorch implementation of a deep metric learning technique called "Magnet Loss" from Facebook AI Research (FAIR) in ICLR 2016.
Stars: ✭ 217 (+416.67%)
NCE-lossTensorflow NCE loss in Keras
Stars: ✭ 30 (-28.57%)
SegsortSegSort: Segmentation by Discriminative Sorting of Segments
Stars: ✭ 130 (+209.52%)
S-WMDCode for Supervised Word Mover's Distance (SWMD)
Stars: ✭ 90 (+114.29%)
PvsePolysemous Visual-Semantic Embedding for Cross-Modal Retrieval (CVPR 2019)
Stars: ✭ 93 (+121.43%)
ePillID-benchmarkePillID Dataset: A Low-Shot Fine-Grained Benchmark for Pill Identification (CVPR 2020 VL3)
Stars: ✭ 54 (+28.57%)
Metric LearnMetric learning algorithms in Python
Stars: ✭ 1,125 (+2578.57%)
GPQGeneralized Product Quantization Network For Semi-supervised Image Retrieval - CVPR 2020
Stars: ✭ 60 (+42.86%)
Deep-Learning-Mahjong---Reinforcement learning (RL) implementation of imperfect information game Mahjong using markov decision processes to predict future game states
Stars: ✭ 45 (+7.14%)
MinkLocMultimodalMinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
Stars: ✭ 65 (+54.76%)
Npair loss pytorchImproved Deep Metric Learning with Multi-class N-pair Loss Objective
Stars: ✭ 75 (+78.57%)
Batch Dropblock NetworkOfficial source code of "Batch DropBlock Network for Person Re-identification and Beyond" (ICCV 2019)
Stars: ✭ 304 (+623.81%)
CatalystAccelerated deep learning R&D
Stars: ✭ 2,804 (+6576.19%)
TCEThis repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).
Stars: ✭ 51 (+21.43%)
Pytorch Image RetrievalA PyTorch framework for an image retrieval task including implementation of N-pair Loss (NIPS 2016) and Angular Loss (ICCV 2017).
Stars: ✭ 203 (+383.33%)
efficient softmaxBlackOut and Adaptive Softmax for language models by Chainer
Stars: ✭ 12 (-71.43%)
TreeRepLearning Tree structures and Tree metrics
Stars: ✭ 18 (-57.14%)
Dml cross entropyCode for the paper "A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses" (ECCV 2020 - Spotlight)
Stars: ✭ 117 (+178.57%)
scLearnscLearn:Learning for single cell assignment
Stars: ✭ 26 (-38.1%)
Negative Margin.few ShotPyTorch implementation of “Negative Margin Matters: Understanding Margin in Few-shot Classification”
Stars: ✭ 101 (+140.48%)
tf retrieval baselineA Tensorflow retrieval (space embedding) baseline. Metric learning baseline on CUB and Stanford Online Products.
Stars: ✭ 39 (-7.14%)
PointglrGlobal-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds (CVPR 2020)
Stars: ✭ 86 (+104.76%)
Open ReidOpen source person re-identification library in python
Stars: ✭ 1,144 (+2623.81%)
triplet-loss-pytorchHighly efficient PyTorch version of the Semi-hard Triplet loss ⚡️
Stars: ✭ 79 (+88.1%)
Open UcnThe first fully convolutional metric learning for geometric/semantic image correspondences.
Stars: ✭ 60 (+42.86%)
Prototypical NetworksCode for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
Stars: ✭ 705 (+1578.57%)
visual-compatibilityContext-Aware Visual Compatibility Prediction (https://arxiv.org/abs/1902.03646)
Stars: ✭ 92 (+119.05%)
Additive Margin SoftmaxThis is the implementation of paper <Additive Margin Softmax for Face Verification>
Stars: ✭ 464 (+1004.76%)
MinkLoc3DMinkLoc3D: Point Cloud Based Large-Scale Place Recognition
Stars: ✭ 83 (+97.62%)
proxy-synthesisOfficial PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)
Stars: ✭ 30 (-28.57%)
HardnetHardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"
Stars: ✭ 350 (+733.33%)
lfdaLocal Fisher Discriminant Analysis in R
Stars: ✭ 74 (+76.19%)
dmlR package for Distance Metric Learning
Stars: ✭ 58 (+38.1%)
Learning-Lab-C-LibraryThis library provides a set of basic functions for different type of deep learning (and other) algorithms in C.This deep learning library will be constantly updated
Stars: ✭ 20 (-52.38%)
SPMLUniversal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning
Stars: ✭ 81 (+92.86%)
MHCLNDeep Metric and Hash Code Learning Network for Content Based Retrieval of Remote Sensing Images
Stars: ✭ 30 (-28.57%)
SPL-ADVisEPyTorch code for BMVC 2018 paper: "Self-Paced Learning with Adaptive Visual Embeddings"
Stars: ✭ 20 (-52.38%)