Multi-Domain Few-Shot Learning and Dataset for Agricultural Applications

Automatic classification of pests and plants (both healthy and diseased) is of paramount importance in agriculture to improve yield. Conventional deep learning models based on convolutional neural networks require thousands of labeled examples per category. In this work we propose a method to learn from a few samples to automatically classify different pests, plants, and their diseases, using Few-Shot Learning (FSL). We learn a feature extractor to generate embeddings and then update the embeddings using Transformers. Using Mahalanobis distance, a class-covariance-based metric, we then calculate the similarity of the transformed embeddings with the embedding of the image to be classified. Using our proposed architecture, we conduct extensive experiments on multiple datasets showing the effectiveness of our proposed model. We conduct 42 experiments in total to comprehensively analyze the model and it achieves up to 14 benchmarks on two datasets. We also compile a new FSL dataset containing images of healthy and diseased plants taken in real-world settings. Using our proposed architecture which has been shown to outperform several existing FSL architectures in agriculture, we provide strong baselines on our newly proposed dataset.

READ FULL TEXT

page 4

page 5

page 6

research
04/04/2020

Optimization of Image Embeddings for Few Shot Learning

In this paper we improve the image embeddings generated in the graph neu...
research
05/27/2020

Looking back to lower-level information in few-shot learning

Humans are capable of learning new concepts from small numbers of exampl...
research
08/25/2021

Learning Class-level Prototypes for Few-shot Learning

Few-shot learning aims to recognize new categories using very few labele...
research
11/10/2022

Few-shot Classification with Hypersphere Modeling of Prototypes

Metric-based meta-learning is one of the de facto standards in few-shot ...
research
12/13/2019

Multi-level Similarity Learning for Low-Shot Recognition

Low-shot learning indicates the ability to recognize unseen objects base...
research
01/06/2023

Exploring Efficient Few-shot Adaptation for Vision Transformers

The task of Few-shot Learning (FSL) aims to do the inference on novel ca...
research
01/23/2020

Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation

Few-shot classification aims to recognize novel categories with only few...

Please sign up or login with your details

Forgot password? Click here to reset