Contrastive multi-view subspace clustering of hyperspectral images based on graph convolutional networks
High-dimensional and complex spectral structures make the clustering of hyperspectral
images (HSIs) a challenging task. Subspace clustering is an effective approach for …
images (HSIs) a challenging task. Subspace clustering is an effective approach for …
Few-shot learning under domain shift: Attentional contrastive calibrated transformer of time series for fault diagnosis under sharp speed variation
The domain shift of sample distribution caused by sharp speed variation dissatisfies the
general assumption of stationary conditions, which renders a severe challenge for a majority …
general assumption of stationary conditions, which renders a severe challenge for a majority …
Hyperspectral image classification with contrastive graph convolutional network
Recently, graph convolutional network (GCN) has been widely used in hyperspectral image
(HSI) classification due to its satisfactory performance. However, the number of labeled …
(HSI) classification due to its satisfactory performance. However, the number of labeled …
Equimod: An equivariance module to improve self-supervised learning
A Devillers, M Lefort - arXiv preprint arXiv:2211.01244, 2022 - arxiv.org
Self-supervised visual representation methods are closing the gap with supervised learning
performance. These methods rely on maximizing the similarity between embeddings of …
performance. These methods rely on maximizing the similarity between embeddings of …
Equimod: An equivariance module to improve visual instance discrimination
A Devillers, M Lefort - International Conference on Learning …, 2023 - hal.science
Recent self-supervised visual representation methods are closing the gap with supervised
learning performance. Most of these successful methods rely on maximizing the similarity …
learning performance. Most of these successful methods rely on maximizing the similarity …
Interpretable Alzheimer's Disease Classification Via a Contrastive Diffusion Autoencoder
In visual object classification, humans often justify their choices by comparing objects to
prototypical examples within that class. We may therefore increase the interpretability of …
prototypical examples within that class. We may therefore increase the interpretability of …
Guarding Barlow Twins Against Overfitting with Mixed Samples
Self-supervised Learning (SSL) aims to learn transferable feature representations for
downstream applications without relying on labeled data. The Barlow Twins algorithm …
downstream applications without relying on labeled data. The Barlow Twins algorithm …
EslaXDET: A new X-ray baggage security detection framework based on self-supervised vision transformers
J Wu, X Xu - Engineering Applications of Artificial Intelligence, 2024 - Elsevier
Deep learning-based X-ray detection of hazardous materials is crucial for public safety, as it
can automatically detect them in baggage. However, most existing algorithms for X-ray …
can automatically detect them in baggage. However, most existing algorithms for X-ray …
Multilevel contrast strategy for unpaired image-to-image translation
Contrastive learning for unpaired image-to-image translation utilizes adversarial loss to
ensure the realism of generated images in the target domain and incorporates pixel-wise …
ensure the realism of generated images in the target domain and incorporates pixel-wise …
Effective Traffic Prediction with Self-Supervised Contrastive Learning
Y Song - 2022 IEEE 8th International Conference on Computer …, 2022 - ieeexplore.ieee.org
Taxi demand prediction has recently attracted increasing research interest due to the
growing availability of large-scale traffic data, which could empower various real-world …
growing availability of large-scale traffic data, which could empower various real-world …