34 datasets found

Prototypical contrastive learning of unsupervised representations.

A simple framework for contrastive learning of visual representations.

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong...

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new...

Self-supervised learning: Generative or contrastive.

Footpath mapping, modeling, and analysis can provide important geospatial insights to many fields of study, including transport, health, environment and urban planning.

A simple data mixing prior for improving self-supervised learning.

Recent self-supervised visual representation methods are closing the gap with supervised learning performance. Most of these successful methods rely on maximizing the similarity...

Self-supervised learning dataset for TransUNet pretraining

The proposed method is a self-supervised learning approach for visual representation learning, which can explicitly capture the local context of an image while preserving the...

SSL4EO-S12: A large-scale, globally distributed, multi-temporal and multi-sensor dataset for self-supervised learning in Earth observation.

Self-supervised monocular depth estimation has gathered no-table interest since it can liberate training from dependency on depth annotations. In monocular video training case,...

A self-supervised and semi-supervised learning for Mars segmentation dataset.

Self-supervised representation learning for Vision Transformers (ViT) to mitigate the greedy needs of ViT networks for very large fully-annotated datasets.