AI RESEARCH
TwistNet-2D: Learning Second-Order Channel Interactions via Spiral Twisting for Texture Recognition
arXiv CS.CV
•
ArXi:2602.07262v3 Announce Type: replace 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.