iCassava 2019 Fine-Grained Visual Categorization Challenge

TL;DR

This paper introduces the iCassava 2019 challenge, providing a dataset and benchmark for fine-grained visual categorization of cassava leaf diseases to aid in disease monitoring and yield improvement.

Contribution

It presents a new dataset and challenge for cassava disease classification, encouraging semi-supervised learning approaches for fine-grained visual categorization.

Findings

Dataset of labeled and unlabeled cassava leaves provided

Challenge promotes development of semi-supervised algorithms

Potential to improve disease diagnosis accuracy

Abstract

Viral diseases are major sources of poor yields for cassava, the 2nd largest provider of carbohydrates in Africa.At least 80% of small-holder farmer households in Sub-Saharan Africa grow cassava. Since many of these farmers have smart phones, they can easily obtain photos of dis-eased and healthy cassava leaves in their farms, allowing the opportunity to use computer vision techniques to monitor the disease type and severity and increase yields. How-ever, annotating these images is extremely difficult as ex-perts who are able to distinguish between highly similar dis-eases need to be employed. We provide a dataset of labeled and unlabeled cassava leaves and formulate a Kaggle challenge to encourage participants to improve the performance of their algorithms using semi-supervised approaches. This paper describes our dataset and challenge which is part of the Fine-Grained Visual Categorization workshop at CVPR2019.