paper-with-me

Papers

Improved Baselines with Momentum Contrastive Learning

2020-03-09 · Xinlei Chen, Haoqi Fan, Ross Girshick, Kaiming He

Contrastive unsupervised learning has recently shown encouraging progress, e.g., in Momentum Contrast (MoCo) and SimCLR. In this note, we verify the effectiveness of two of SimCLR's design improvements by implementing them in the MoCo framework. With simple modifications to MoCo---namely, using an MLP projection head and more data augmentation---we establish stronger baselines that outperform SimCLR and do not require large training batches. We hope this will make state-of-the-art unsupervised learning research more accessible. Code will be made public.

📄 PDF Abstract BibTeX arXiv:2003.04297

Code (36)

facebookresearch/moco 공식 구현 pytorch
1170500804/MoCo pytorch
AidenDurrant/MoCo-Pytorch pytorch
AndrewTal/MoCo-Pytorch pytorch
ClaudiaShu/SSL-FER pytorch
CoinCheung/denseCL pytorch
Evgeneus/MoCo pytorch
Ghiara/diva pytorch
HobbitLong/PyContrast pytorch
OML-Team/open-metric-learning pytorch
Pangoraw/GeoSSL pytorch
PaperCodeReview/MoCo-TF tf
Seonghoon-Yu/MoCov2_Pytorch_tutorial pytorch
TRAILab/ST-SLidR pytorch
Westlake-AI/openmixup pytorch
a07458666/simsiamfacenet pytorch
aheuillet/nasiam pytorch
alibaba/EasyCV pytorch
cjrd/self-supervised-pretraining pytorch
danielgordon10/vince pytorch
derrickwang005/mosrep pytorch
facebookresearch/simsiam pytorch
kikacaty/adv_guide pytorch
lavoiems/Cats-UDT pytorch
lavoiems/SADt pytorch
lavoiems/SPUDT pytorch
lightly-ai/lightly pytorch
linwenye/light-moco pytorch
open-mmlab/mmdetection pytorch
open-mmlab/mmselfsup pytorch
ppwwyyxx/moco.tensorflow tf
robml/Deep-Learning-SSL-MoCo-SP21 pytorch
smartdanny/MoCoV2_CIFAR10 pytorch
szq0214/S2-BNN pytorch
technioncomputationalmrilab/colorectal_cancer_ai pytorch
vturrisi/solo-learn pytorch

Tasks

Contrastive LearningData AugmentationImage ClassificationPerson Re-IdentificationRepresentation LearningSelf-Supervised Image ClassificationSelf-Supervised Person Re-Identification

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
InfoNCE 설명 없음
Random Gaussian Blur Random Gaussian Blur is an image data augmentation technique where we randomly blur the image using a Gaussian distribution. Image Source:…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
SGD with Momentum 설명 없음
Random Horizontal Flip RandomHorizontalFlip is a type of image data augmentation which horizontally flips a given image with a given probability. Image Credit: [Apache…
Random Resized Crop 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…

Similar Papers 제목 키워드 기반

Momentum Contrastive Pre-training for Question Answering

2022-12-12 · Minda Hu, Muzhi Li, Yasheng Wang, Irwin King

Existing pre-training methods for extractive Question Answering (QA) generate cloze-like queries different from natural questions in syntax structure, which could overfit pre-trained models to simple keyword matching. In…

BenchmarkingContrastive LearningExtractive Question-AnsweringNatural Questions+1

CoCoSoDa: Effective Contrastive Learning for Code Search

2022-04-07 · Ensheng Shi, Yanlin Wang, Wenchao Gu, Lun Du 외

Code search aims to retrieve semantically relevant code snippets for a given natural language query. Recently, many approaches employing contrastive learning have shown promising results on code representation learning a…

Code SearchContrastive LearningData AugmentationRepresentation Learning

Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learning

2020-12-13 · Wei Xia, Chunlei Zhang, Chao Weng, Meng Yu 외

In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework…

ClusteringContrastive LearningRepresentation LearningSpeaker Verification+1

AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Prediction

2025-07-02 · Bin Rao, Haicheng Liao, Yanchen Guan, Chengyue Wang 외 arxiv

Accurately predicting the future trajectories of traffic agents is essential in autonomous driving. However, due to the inherent imbalance in trajectory distributions, tail data in natural datasets often represents more …

Trajectory PredictionContrastive LearningAutonomous Driving

Self-Supervised Visual Representation Learning via Residual Momentum

2022-11-17 · Trung X. Pham, Axi Niu, Zhang Kang, Sultan Rizky Madjid 외

Self-supervised learning (SSL) approaches have shown promising capabilities in learning the representation from unlabeled data. Amongst them, momentum-based frameworks have attracted significant attention. Despite being …

Contrastive LearningRepresentation LearningSelf-Supervised Learning