paper-with-me

Papers

Data-Efficient Image Recognition with Contrastive Predictive Coding

2019-05-22 · ICML 2020 1 · Olivier J. Hénaff, Aravind Srinivas, Jeffrey De Fauw, Ali Razavi, Carl Doersch, S. M. Ali Eslami, Aaron van den Oord

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.

📄 PDF Abstract BibTeX arXiv:1905.09272

Code (4)

SeonghoBaek/CPC tf
SeonghoBaek/FrameSequencePrediction tf
mf1024/Contrastive-Predictive-Coding-for-Image-Recognition-in-PyTorch pytorch
philip-bachman/amdim-public pytorch

Tasks

Contrastive LearningGeneral Classificationobject-detectionObject DetectionSelf-Supervised Image ClassificationSemi-Supervised Image ClassificationTransfer Learning

Methods 이 논문이 사용한 방법론

InfoNCE 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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
RoIPool 설명 없음
Faster R-CNN Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network…
Random Resized Crop 설명 없음

Similar Papers 제목 키워드 기반

Guided contrastive self-supervised pre-training for automatic speech recognition

2022-10-22 · Aparna Khare, Minhua Wu, Saurabhchand Bhati, Jasha Droppo 외

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+1

Contrastive Predictive Coding for Human Activity Recognition

2020-12-09 · Harish Haresamudram, Irfan Essa, Thomas Ploetz

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 Recognition

Contrastive Predictive Coding for Anomaly Detection

2021-07-16 · Puck de Haan, Sindy Löwe

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+1

Contrastive Predictive Coding Based Feature for Automatic Speaker Verification

2019-04-01 · Cheng-I Lai

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 Verification

Contrastive Unsupervised Learning for Speech Emotion Recognition

2021-02-12 · Mao Li, Bo Yang, Joshua Levy, Andreas Stolcke 외

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