paper-with-me

Papers

Momentum Contrast for Unsupervised Visual Representation Learning

2019-11-13 · CVPR 2020 6 · Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks.

📄 PDF Abstract BibTeX arXiv:1911.05722

Code (44)

facebookresearch/moco 공식 구현 pytorch
ppwwyyxx/moco.tensorflow 공식 구현 tf
1170500804/MoCo pytorch
AidenDurrant/MoCo-Pytorch pytorch
AndrewTal/MoCo-Pytorch pytorch
CoinCheung/denseCL pytorch
Evgeneus/MoCo pytorch
HobbitLong/CMC pytorch
HobbitLong/PyContrast pytorch
KevinMusgrave/pytorch-metric-learning pytorch
KevinMusgrave/pytorch_metric_learning pytorch
LeiLiu-byte/the-Essence-of-LT-Rocognition pytorch
PaddlePaddle/PASSL/blob/main/docs/Train_MoCo_model.md paddle
Pangoraw/GeoSSL pytorch
PaperCodeReview/MoCo-TF tf
Westlake-AI/openmixup pytorch
YyzHarry/imbalanced-semi-self pytorch
ali-nsua/DISCERN pytorch
alibaba/EasyCV pytorch
alihassanijr/DISCERN pytorch
amazon-research/exponential-moving-average-normalization pytorch
beresandras/contrastive-classification-keras tf
bl0/moco pytorch
davidsvy/hard-negative-mixing pytorch
ehsanik/muscleTorch pytorch
ernie1/pi-nas pytorch
facebookresearch/vissl pytorch
giakou4/pyssl pytorch
giakoumoglou/synco pytorch
joshr17/IFM pytorch
kikacaty/adv_guide pytorch
leftthomas/moco pytorch
lightly-ai/lightly pytorch
linwenye/light-moco pytorch
open-mmlab/mmdetection pytorch
open-mmlab/mmselfsup pytorch
smartdanny/MoCoV2_CIFAR10 pytorch
srinidhiPY/SSL_CR_Histo pytorch
szq0214/CMC_with_Image_Mixture pytorch
tranc012/SMILE-Rep pytorch
trannhiem/ma_ssrl_pytorch pytorch
xiangli13/MoCo tf
yangyucheng000/MoCo mindspore
zhangyifei01/EIR pytorch

Tasks

Contrastive LearningImage ClassificationRepresentation LearningSelf-Supervised Image Classification

Methods 이 논문이 사용한 방법론

InfoNCE 설명 없음
Random Grayscale Random Grayscale is an image data augmentation that converts an image to grayscale with probability $p$.
Random Horizontal Flip RandomHorizontalFlip is a type of image data augmentation which horizontally flips a given image with a given probability. Image Credit: [Apache…
ColorJitter 설명 없음
Random Resized Crop 설명 없음
FPN 설명 없음
RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…
Mask R-CNN Mask R-CNN extends Faster R-CNN to solve instance segmentation tasks. It achieves this by adding a branch for predicting an…

Similar Papers 제목 키워드 기반

UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning

2021-03-19 · Zhigang Dai, Bolun Cai, Yugeng Lin, Junying Chen

Momentum Contrast (MoCo) achieves great success for unsupervised visual representation. However, there are a lot of supervised and semi-supervised datasets, which are already labeled. To fully utilize the label annotatio…

Representation Learning

Unsupervised Visual Representation Learning by Synchronous Momentum Grouping

2022-07-13 · Bo Pang, Yifan Zhang, Yaoyi Li, Jia Cai 외

In this paper, we propose a genuine group-level contrastive visual representation learning method whose linear evaluation performance on ImageNet surpasses the vanilla supervised learning. Two mainstream unsupervised lea…

ClusteringContrastive LearningLinear evaluationRepresentation Learning+1

Masked Contrastive Representation Learning

2022-11-11 · Yuchong Yao, Nandakishor Desai, Marimuthu Palaniswami

Masked image modelling (e.g., Masked AutoEncoder) and contrastive learning (e.g., Momentum Contrast) have shown impressive performance on unsupervised visual representation learning. This work presents Masked Contrastive…

Contrastive LearningData AugmentationDecoderRepresentation Learning

Momentum Contrast Speaker Representation Learning

2020-10-22

Unsupervised representation learning has shown remarkable achievement by reducing the performance gap with supervised feature learning, especially in the image domain. In this study, to extend the technique of unsupervis…

Contrastive LearningMetric LearningRepresentation LearningSpeaker Recognition+1

CO2: Consistent Contrast for Unsupervised Visual Representation Learning

2020-10-05 · ICLR 2021 1 · Chen Wei, Huiyu Wang, Wei Shen, Alan Yuille

Contrastive learning has been adopted as a core method for unsupervised visual representation learning. Without human annotation, the common practice is to perform an instance discrimination task: Given a query image cro…

Contrastive Learningimage-classificationImage Classificationobject-detection+4