Chaotic maps act as augmentations in contrastive pre-training to learn topologically robust texture features, outperforming SOTA on six benchmarks when combined with attention-based fusion.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Convolutional autoencoder pretraining plus deep filter banks and Fisher vector pooling yields improved texture classification accuracy and lower complexity than transformer-based masked autoencoders on standard texture datasets.
citing papers explorer
-
Chaotic Contrastive Learning for Robust Texture Classification
Chaotic maps act as augmentations in contrastive pre-training to learn topologically robust texture features, outperforming SOTA on six benchmarks when combined with attention-based fusion.
-
A self-supervised learning approach to deep filter banks for texture recognition
Convolutional autoencoder pretraining plus deep filter banks and Fisher vector pooling yields improved texture classification accuracy and lower complexity than transformer-based masked autoencoders on standard texture datasets.