all AI news
Hilbert Flattening: a Locality-Preserving Matrix Unfolding Method for Visual Discrimination. (arXiv:2202.10240v7 [cs.CV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
Flattening is essential in computer vision by converting multi-dimensional
feature maps or images into one-dimensional vectors. However, existing
flattening approaches neglect the preservation of local smoothness, which can
impact the representational learning capacity of vision models. In this paper,
we propose Hilbert curve flattening as an innovative method to preserve
locality in flattened matrices. We compare it with the commonly used Zigzag
operation and demonstrate that Hilbert curve flattening can better retain the
spatial relationships and local smoothness of the …
arxiv capacity computer computer vision cs.cv discrimination feature images impact maps matrix paper preservation vectors vision vision models visual