Papers Self-Supervised Image Classification
“Self-Supervised Image Classification” 태그가 달린 논문 110편 · 필터 해제
Consensus Clustering With Unsupervised Representation Learning
Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must either be closer in the repre…
ClusteringData AugmentationDeep ClusteringEnsemble Learning+6Generative Pretraining from Pixels
Inspired by progress in unsupervised representation learning for natural language, we examine whether similar models can learn useful representations for images. We train a sequence Transformer to auto-regressively predi…
Image ClassificationRepresentation LearningSelf-Supervised Image ClassificationBig Self-Supervised Models are Strong Semi-Supervised Learners
One paradigm for learning from few labeled examples while making best use of a large amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. Although this paradigm uses unlabeled data in …
Self-Supervised Image ClassificationSemi-Supervised Image ClassificationUnsupervised Learning of Visual Features by Contrasting Cluster Assignments
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and…
Contrastive LearningData AugmentationImage ClassificationSelf-Supervised Image Classification+1Bootstrap your own latent: A new approach to self-supervised Learning
We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from …
Image ClassificationLinear evaluationPerson Re-IdentificationRepresentation Learning+4What Makes for Good Views for Contrastive Learning?
Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view cho…
Contrastive LearningData AugmentationGeneral ClassificationInstance Segmentation+6Prototypical Contrastive Learning of Unsupervised Representations
This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level …
ClusteringContrastive LearningRepresentation LearningSelf-Supervised Image Classification+2Improved Baselines with Momentum Contrastive Learning
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 th…
Contrastive LearningData AugmentationImage ClassificationPerson Re-Identification+3A Simple Framework for Contrastive Learning of Visual Representations
This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures…
Contrastive LearningImage ClassificationObject RecognitionPerson Re-Identification+4Self-Supervised Learning of Pretext-Invariant Representations
The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic annotations for a large training set of images. Many …
Contrastive Learningobject-detectionObject DetectionRepresentation Learning+3Momentum Contrast for Unsupervised Visual Representation Learning
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 enco…
Contrastive LearningImage ClassificationRepresentation LearningSelf-Supervised Image ClassificationSelf-labelling via simultaneous clustering and representation learning
Combining clustering and representation learning is one of the most promising approaches for unsupervised learning of deep neural networks. However, doing so naively leads to ill posed learning problems with degenerate s…
ClusteringContrastive LearningImage ClusteringRepresentation Learning+2On Mutual Information Maximization for Representation Learning
Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data. This comes with sever…
Inductive BiasRepresentation LearningSelf-Supervised Image ClassificationLarge Scale Adversarial Representation Learning
Adversarially trained generative models (GANs) have recently achieved compelling image synthesis results. But despite early successes in using GANs for unsupervised representation learning, they have since been supersede…
Contrastive LearningImage GenerationRepresentation LearningSelf-Supervised Image Classification+2Contrastive Multiview Coding
Humans view the world through many sensory channels, e.g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, heard by the right ear. Each view is noisy and incomplete, b…
Contrastive LearningSelf-Supervised Action RecognitionSelf-Supervised Image ClassificationLearning Representations by Maximizing Mutual Information Across Views
We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views o…
Data AugmentationImage ClassificationLinear evaluationRepresentation Learning+2Putting An End to End-to-End: Gradient-Isolated Learning of Representations
We propose a novel deep learning method for local self-supervised representation learning that does not require labels nor end-to-end backpropagation but exploits the natural order in data instead. Inspired by the observ…
Representation LearningSelf-Supervised Audio ClassificationSelf-Supervised Image ClassificationSelf-Supervised LearningData-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 repres…
Contrastive LearningGeneral Classificationobject-detectionObject Detection+3Unsupervised Pre-Training of Image Features on Non-Curated Data
Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervised feature learning have focused on eit…
ClusteringSelf-Supervised Image ClassificationUnsupervised Pre-trainingLocal Aggregation for Unsupervised Learning of Visual Embeddings
Unsupervised approaches to learning in neural networks are of substantial interest for furthering artificial intelligence, both because they would enable the training of networks without the need for large numbers of exp…
ClusteringContrastive Learningobject-detectionObject Detection+4