Achieving Rotation Invariance in Convolution Operations: Shifting from Data-Driven to Mechanism-Assured

arXiv:2404.11309v1 Announce Type: new
Abstract: Achieving rotation invariance in deep neural networks without relying on data has always been a hot research topic. Intrinsic rotation invariance can enhance the model's feature representation capability, enabling better performance in tasks such as multi-orientation object recognition and detection. Based on various types of non-learnable operators, including gradient, sort, local binary pattern, maximum, etc., this paper designs a set of new convolution operations that are natually invariant to arbitrary rotations. Unlike most previous studies, …

abstract arxiv capability convolution cs.cv data data-driven detection enabling feature hot intrinsic networks neural networks object operations performance recognition representation research rotation tasks type types