A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends
Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …
achieve satisfactory performance. However, the process of collecting and labeling such data …
Advancing plain vision transformer toward remote sensing foundation model
Large-scale vision foundation models have made significant progress in visual tasks on
natural images, with vision transformers (ViTs) being the primary choice due to their good …
natural images, with vision transformers (ViTs) being the primary choice due to their good …
An empirical study of remote sensing pretraining
Deep learning has largely reshaped remote sensing (RS) research for aerial image
understanding and made a great success. Nevertheless, most of the existing deep models …
understanding and made a great success. Nevertheless, most of the existing deep models …
Ddpm-cd: Remote sensing change detection using denoising diffusion probabilistic models
Human civilization has an increasingly powerful influence on the earth system, and earth
observations are an invaluable tool for assessing and mitigating the negative impacts. To …
observations are an invaluable tool for assessing and mitigating the negative impacts. To …
Cmid: A unified self-supervised learning framework for remote sensing image understanding
Self-supervised learning (SSL) has gained wide-spread attention in the remote sensing (RS)
and Earth observation (EO) communities owing to its ability to learn task-agnostic …
and Earth observation (EO) communities owing to its ability to learn task-agnostic …
Vitpose++: Vision transformer for generic body pose estimation
In this paper, we show the surprisingly good properties of plain vision transformers for body
pose estimation from various aspects, namely simplicity in model structure, scalability in …
pose estimation from various aspects, namely simplicity in model structure, scalability in …
Embedding global contrastive and local location in self-supervised learning
Self-supervised representation learning (SSL) typically suffers from inadequate data
utilization and feature-specificity due to the suboptimal sampling strategy and the …
utilization and feature-specificity due to the suboptimal sampling strategy and the …
ViTPose++: Vision Transformer Foundation Model for Generic Body Pose Estimation
In this paper, we show the surprisingly good properties of plain vision transformers for body
pose estimation from various aspects, namely simplicity in model structure, scalability in …
pose estimation from various aspects, namely simplicity in model structure, scalability in …
I3cl: Intra-and inter-instance collaborative learning for arbitrary-shaped scene text detection
Existing methods for arbitrary-shaped text detection in natural scenes face two critical
issues, ie,(1) fracture detections at the gaps in a text instance; and (2) inaccurate detections …
issues, ie,(1) fracture detections at the gaps in a text instance; and (2) inaccurate detections …
LESSL: Can LEGO sampling and collaborative optimization contribute to self-supervised learning?
Self-supervised visual representation learning (SSL) aims to extract the most distinctive
features from unlabeled datasets to overcome challenges of labor-intensive and time …
features from unlabeled datasets to overcome challenges of labor-intensive and time …