Analyze weeds classification with visual explanation based on Convolutional Neural Networks

• 발행기관: 한국스마트미디어학회
• 저자명: Hoang-Trong Vo Gwang-Hyun Yu Huy-Toan Nguyen Ju-Hwan Lee Thanh-Vu Dang Jin-Young Kim
• 간행물 정보: 『스마트미디어저널』Vol8, No.3, 31~40쪽, 전체 10쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2019.09.30

영문 초록

To understand how a Convolutional Neural Network (CNN) model captures the features of a pattern to determine which class it belongs to, in this paper, we use Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize and analyze how well a CNN model behave on the CNU weeds dataset. We apply this technique to Resnet model and figure out which features this model captures to determine a specific class, what makes the model get a correct/wrong classification, and how those wrong label images can cause a negative effect to a CNN model during the training process. In the experiment, Grad-CAM highlights the important regions of weeds, depending on the patterns learned by Resnet, such as the lobe and limb on 미국가막사리, or the entire leaf surface on 단풍잎돼지풀. Besides, Grad-CAM points out a CNN model can localize the object even though it is trained only for the classification problem.

목차

Ⅰ. INTRODUCTION

Ⅱ. RELATED WORK

Ⅲ. CNU WEEDS DATASET

Ⅳ. EXPERIMENT

Ⅴ. CONCLUSION

키워드

Grad-CAM CNN visualization Resnet