# Chinese Herbal Recognition based on Competitive Attentional Fusion of Multi-hierarchies Pyramid Features

## TL;DR

This paper introduces a novel competitive attentional fusion pyramid network for Chinese herbal recognition, leveraging multi-level feature relationships and attention mechanisms to improve accuracy in herbal image classification.

## Contribution

The study proposes a new CNN architecture with competitive attentional fusion and multi-hierarchy pyramid features specifically designed for Chinese herbal recognition.

## Key findings

- The proposed model outperforms existing methods on the new herbal datasets.
- The attention mechanisms effectively enhance feature representation.
- The datasets will be publicly released for further research.

## Abstract

Convolution neural netwotks (CNNs) are successfully applied in image recognition task. In this study, we explore the approach of automatic herbal recognition with CNNs and build the standard Chinese herbs datasets firstly. According to the characteristics of herbal images, we proposed the competitive attentional fusion pyramid networks to model the features of herbal image, which mdoels the relationship of feature maps from different levels, and re-weights multi-level channels with channel-wise attention mechanism. In this way, we can dynamically adjust the weight of feature maps from various layers, according to the visual characteristics of each herbal image. Moreover, we also introduce the spatial attention to recalibrate the misaligned features caused by sampling in features amalgamation. Extensive experiments are conducted on our proposed datasets and validate the superior performance of our proposed models. The Chinese herbs datasets will be released upon acceptance to facilitate the research of Chinese herbal recognition.