Data-Efficient Image Recognition with Contrastive Predictive Coding
Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make the variability in natural signals more predictable. We therefore revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations. This new implementation produces features which support state-of-the-art linear classification accuracy on the ImageNet dataset. When used as input for non-linear classification with deep neural networks, this representation allows us to use 2-5x less labels than classifiers trained directly on image pixels. Finally, this unsupervised representation substantially improves transfer learning to object detection on the PASCAL VOC dataset, surpassing fully supervised pre-trained ImageNet classifiers.
Code (4)
Tasks
Contrastive LearningGeneral Classificationobject-detectionObject DetectionSelf-Supervised Image ClassificationSemi-Supervised Image ClassificationTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Guided contrastive self-supervised pre-training for automatic speech recognition
Contrastive Predictive Coding (CPC) is a representation learning method that maximizes the mutual information between intermediate latent representations and the output of a given model. It can be used to effectively ini…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Representation Learningspeech-recognition+1Contrastive Predictive Coding for Human Activity Recognition
Feature extraction is crucial for human activity recognition (HAR) using body-worn movement sensors. Recently, learned representations have been used successfully, offering promising alternatives to manually engineered f…
Activity RecognitionHuman Activity RecognitionContrastive Predictive Coding for Anomaly Detection
Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becomi…
Anomaly DetectionAnomaly SegmentationContrastive LearningRepresentation Learning+1Contrastive Predictive Coding Based Feature for Automatic Speaker Verification
This thesis describes our ongoing work on Contrastive Predictive Coding (CPC) features for speaker verification. CPC is a recently proposed representation learning framework based on predictive coding and noise contrasti…
Representation LearningSpeaker VerificationContrastive Unsupervised Learning for Speech Emotion Recognition
Speech emotion recognition (SER) is a key technology to enable more natural human-machine communication. However, SER has long suffered from a lack of public large-scale labeled datasets. To circumvent this problem, we i…
Emotion RecognitionRepresentation LearningSpeech Emotion Recognition