Weakly Supervised Attention-based Models Using Activation Maps for Citrus Mite and Insect Pest Classification

TL;DR

This paper introduces a novel attention-based activation map method for classifying tiny pest regions in citrus images, achieving superior accuracy and localization without explicit bounding box labels.

Contribution

The work presents a Two-Weighted Activation Mapping technique integrated into a two-stage attention-based MIL framework, improving tiny pest classification and localization in weakly supervised settings.

Findings

Outperforms existing weakly supervised methods by at least 16 percentage points.

Effectively localizes pests without explicit bounding box annotations.

Demonstrates robustness across challenging field and benchmark datasets.

Abstract

Citrus juices and fruits are commodities with great economic potential in the international market, but productivity losses caused by mites and other pests are still far from being a good mark. Despite the integrated pest mechanical aspect, only a few works on automatic classification have handled images with orange mite characteristics, which means tiny and noisy regions of interest. On the computational side, attention-based models have gained prominence in deep learning research, and, along with weakly supervised learning algorithms, they have improved tasks performed with some label restrictions. In agronomic research of pests and diseases, these techniques can improve classification performance while pointing out the location of mites and insects without specific labels, reducing deep learning development costs related to generating bounding boxes. In this context, this work proposes an attention-based activation map approach developed to improve the classification of tiny regions called Two-Weighted Activation Mapping, which also produces locations using feature map scores learned from class labels. We apply our method in a two-stage network process called Attention-based Multiple Instance Learning Guided by Saliency Maps. We analyze the proposed approach in two challenging datasets, the Citrus Pest Benchmark, which was captured directly in the field using magnifying glasses, and the Insect Pest, a large pest image benchmark. In addition, we evaluate and compare our models with weakly supervised methods, such as Attention-based Deep MIL and WILDCAT. The results show that our classifier is superior to literature methods that use tiny regions in their classification tasks, surpassing them in all scenarios by at least 16 percentage points. Moreover, our approach infers bounding box locations for salient insects, even training without any location labels.