TwistNet-2D is a new CNN module that uses directional spiral shifts and normalized channel products to model local second-order texture interactions, outperforming larger backbones on four benchmarks with only 3.5% extra parameters.
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
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.
citing papers explorer
-
TwistNet-2D: Learning Second-Order Channel Interactions via Spiral Twisting for Texture Recognition
TwistNet-2D is a new CNN module that uses directional spiral shifts and normalized channel products to model local second-order texture interactions, outperforming larger backbones on four benchmarks with only 3.5% extra parameters.
-
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.