litlas
ログインアカウント作成

Improved Baselines with Momentum Contrastive Learning

著者: Xinlei Chen, Haoqi Fan, Ross B. Girshick, Kaiming He - arXiv 2020 被引用: 2,941

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.

Microsoft COCO: CommonObjects in ContextMicrosoft COCO: Common Objects in ContextFaster R-CNN: TowardsReal-Time Object…Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksDeep Residual Learningfor Image RecognitionDeep Residual Learning for Image RecognitionUnsupervised FeatureLearning via…Unsupervised Feature Learning via Non-Parametric Instance DiscriminationRepresentation Learningwith Contrastive…Representation Learning with Contrastive Predictive CodingLearning Representationsby Maximizing Mutual…Learning Representations by Maximizing Mutual Information Across ViewsData-Efficient ImageRecognition with…Data-Efficient Image Recognition with Contrastive Predictive CodingLearning deeprepresentations by…Learning deep representations by mutual information estimation and maximizationMomentum Contrast forUnsupervised Visual…Momentum Contrast for Unsupervised Visual Representation LearningA Simple Framework forContrastive Learning of…A Simple Framework for Contrastive Learning of Visual RepresentationsContrastive MultiviewCodingContrastive Multiview CodingSelf-Supervised Learningof Pretext-Invariant…Self-Supervised Learning of Pretext-Invariant RepresentationsSelf-supervised learningthrough the eyes of a…Self-supervised learning through the eyes of a childMultimodal ContrastiveTraining for Visual…Multimodal Contrastive Training for Visual Representation LearningDivide and Contrast:Self-supervised Learnin…Divide and Contrast: Self-supervised Learning from Uncurated DataReview onself-supervised image…Review on self-supervised image recognition using deep neural networksA survey on Semi-, Self-and Unsupervised…A survey on Semi-, Self- and Unsupervised Techniques in Image ClassificationUnsupervisedPre-Training for Person…Unsupervised Pre-Training for Person Re-IdentificationTowards Good Practicesfor Efficiently…Towards Good Practices for Efficiently Annotating Large-Scale Image Classification DatasetsMulti-Label ContrastiveLearning for Abstract…Multi-Label Contrastive Learning for Abstract Visual ReasoningTest-AgnosticLong-Tailed Recognition…Test-Agnostic Long-Tailed Recognition by Test-Time Aggregating Diverse Experts with Self-SupervisionSelf-Supervised Learningfrom Images with a…Self-Supervised Learning from Images with a Joint-Embedding Predictive ArchitectureMulti-Mode OnlineKnowledge Distillation…Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation LearningExploring theCoordination of…Exploring the Coordination of Frequency and Attention in Masked Image ModelingImproved Baselines withMomentum Contrastive…Improved Baselines with Momentum Contrastive Learning過去の参考文献中心の論文この論文を引用する論文古い新しい

ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。