Related papers: Self-Supervised Learning with a Multi-Task Latent …

We investigate whether self-supervised learning (SSL) can improve online reinforcement learning (RL) from pixels. We extend the contrastive reinforcement learning framework (e.g., CURL) that jointly optimizes SSL and RL losses and conduct…

Self-Supervised Learning (SSL) for Vision Transformers (ViTs) has recently demonstrated considerable potential as a pre-training strategy for a variety of computer vision tasks, including image classification and segmentation, both in…

Self-supervised learning (SSL) has rapidly emerged as a transformative approach in computer vision, enabling the extraction of rich feature representations from vast amounts of unlabeled data and reducing reliance on costly manual…

We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks. Specifically, by biological plausible training we mean (i) All updates of weights are based on current activities of pre-synaptic…

Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global…

Graph representation learning plays a vital role in processing graph-structured data. However, prior arts on graph representation learning heavily rely on labeling information. To overcome this problem, inspired by the recent success of…

Early cancer detection is crucial for prognosis, but many cancer types lack large labelled datasets required for developing deep learning models. This paper investigates self-supervised learning (SSL) as an alternative to the standard…

Recent research in self-supervised learning (SSL) has shown its capability in learning useful semantic representations from images for classification tasks. Through our work, we study the usefulness of SSL for Fine-Grained Visual…

Two problems often plague medical imaging analysis: 1) Non-availability of large quantities of labeled training data, and 2) Dealing with imbalanced data, i.e., abundant data are available for frequent classes, whereas data are highly…

Collecting large-scale medical datasets with fully annotated samples for training of deep networks is prohibitively expensive, especially for 3D volume data. Recent breakthroughs in self-supervised learning (SSL) offer the ability to…

Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable…

Semi-supervised learning (SSL) has proven to be effective at leveraging large-scale unlabeled data to mitigate the dependency on labeled data in order to learn better models for visual recognition and classification tasks. However, recent…

We propose a metadata-aware self-supervised learning~(SSL)~framework useful for fine-grained classification and ecological mapping of bird species around the world. Our framework unifies two SSL strategies: Contrastive Learning~(CL) and…

Recently, self-supervised learning (SSL) methods have been used in pre-training the segmentation models for 2D and 3D medical images. Most of these methods are based on reconstruction, contrastive learning and consistency regularization.…

Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based…

Self-supervised learning (SSL) is often deployed under changing information, such as shorter histories, missing features, or partially observed images. In these settings, predictions from coarse and refined views should be coherent: before…

Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data…

We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline, consisting of first…

This paper investigates the impact of sampling and pretraining using datasets with different image characteristics on the performance of self-supervised learning (SSL) models for object classification. To do this, we sample two apartment…

Self-supervised learning (SSL), which aims to learn meaningful prior representations from unlabeled data, has been proven effective for skeleton-based action understanding. Different from the image domain, skeleton data possesses sparser…