# TwistNet-2D: Learning Second-Order Channel Interactions via Spiral Twisting for Texture Recognition

arXiv: https://arxiv.org/abs/2602.07262 · HTML: https://mlsanity.com/paper/2602.07262/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [Demystifying Neural Style Transfer](https://mlsanity.com/paper/1701.01036/) (2017)
- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [Compact Bilinear Pooling](https://mlsanity.com/paper/1511.06062/) (2015)
- [Deep Polynomial Neural Networks](https://mlsanity.com/paper/2006.13026/) (2020)
- [Deep TEN: Texture Encoding Network](https://mlsanity.com/paper/1612.02844/) (2016)
- [Is Second-order Information Helpful for Large-scale Visual Recognition?](https://mlsanity.com/paper/1703.08050/) (2017)
- [Low-rank Bilinear Pooling for Fine-Grained Classification](https://mlsanity.com/paper/1611.05109/) (2016)
- [Deep Texture Manifold for Ground Terrain Recognition](https://mlsanity.com/paper/1803.10896/) (2018)
- [RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps](https://mlsanity.com/paper/2303.04554/) (2023)
- [Twisted Convolutional Networks (TCNs): Enhancing Feature Interactions for Non-Spatial Data Classification](https://mlsanity.com/paper/2412.00238/) (2024)

## Abstract (arXiv)

Second-order feature statistics are central to texture recognition, yet existing mechanisms exhibit a structural tension: bilinear pooling and Gram matrices capture global channel correlations but discard spatial structure, whereas self-attention models capture cross-position relations through weighted sums rather than explicit pairwise products. We propose TwistNet-2D, a lightweight module that computes local pairwise channel products under directional spatial displacement, jointly encoding where features co-occur and how they interact. The core component, Spiral-Twisted Channel Interaction (STCI), shifts one feature map along a prescribed direction before L2-normalized channel multiplication, capturing cross-position co-occurrence patterns that characterize structured and periodic textures. Four directional heads are aggregated through content-adaptive channel reweighting, and the result is injected via a sigmoid-gated residual path with near-zero initialization. TwistNet-2D adds only approximately 3.5% parameters and approximately 2% FLOPs over ResNet-18. To isolate the contribution of architectural inductive bias from that of transfer learning, all models in this study are trained from scratch without ImageNet pretraining. Under this protocol, TwistNet-2D consistently surpasses parameter-matched baselines and substantially larger ConvNeXt and Swin Transformer backbones across four texture and fine-grained recognition benchmarks, while the multi-head structure produces interpretable, orientation-selective representations that align with classical texture analysis.