Contrastive Learning with Synthetic Positives
Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-
supervised learning (SSL) techniques by utilizing the similarity of multiple instances within …
supervised learning (SSL) techniques by utilizing the similarity of multiple instances within …
Good Fences Make Good Neighbours
IG Estepa, J Rodríguez-de-Vera… - Proceedings of the …, 2023 - openaccess.thecvf.com
Neighbour contrastive learning enhances the common contrastive learning methods by
introducing neighbour representations to the training of pretext tasks. These algorithms are …
introducing neighbour representations to the training of pretext tasks. These algorithms are …
Learning shared template representation with augmented feature for multi-object pose estimation
Q Luo, TB Xu, F Liu, T Li, Z Wei - Neural Networks, 2024 - Elsevier
Template matching pose estimation methods based on deep learning have made significant
advancements via metric learning or reconstruction learning. Existing approaches primarily …
advancements via metric learning or reconstruction learning. Existing approaches primarily …
Enhancing clustering representations with positive proximity and cluster dispersion learning
Contemporary deep clustering approaches often rely on contrastive or non-contrastive
techniques to acquire effective representations for clustering tasks. Contrastive methods …
techniques to acquire effective representations for clustering tasks. Contrastive methods …
Seeing the Whole in the Parts in Self-Supervised Representation Learning
Recent successes in self-supervised learning (SSL) model spatial co-occurrences of visual
features either by masking portions of an image or by aggressively cropping it. Here, we …
features either by masking portions of an image or by aggressively cropping it. Here, we …
HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms
In this paper, we propose an algorithm that can be used on top of a wide variety of self-
supervised (SSL) approaches to take advantage of hierarchical structures that emerge …
supervised (SSL) approaches to take advantage of hierarchical structures that emerge …
Self-supervised learning for radio-astronomy source classification: a benchmark
The upcoming Square Kilometer Array (SKA) telescope marks a significant step forward in
radio astronomy, presenting new opportunities and challenges for data analysis. Traditional …
radio astronomy, presenting new opportunities and challenges for data analysis. Traditional …