Lacunarity Pooling Layers for Plant Image Classification using Texture Analysis

arXiv:2404.16268v1 Announce Type: new
Abstract: Pooling layers (e.g., max and average) may overlook important information encoded in the spatial arrangement of pixel intensity and/or feature values. We propose a novel lacunarity pooling layer that aims to capture the spatial heterogeneity of the feature maps by evaluating the variability within local windows. The layer operates at multiple scales, allowing the network to adaptively learn hierarchical features. The lacunarity pooling layer can be seamlessly integrated into any artificial neural network architecture. Experimental …

abstract analysis arxiv classification cs.cv feature image information intensity layer maps max novel pixel pooling spatial texture type values