DecapodAI: A Multi-modal Deep-learning-based Tool for Image Classification of Marine Decapoda
Introduction
We collected raw data, performed data cleaning on the raw data and obtained a WoRMS (global data source) based dataset of decapod images.
In this study, we present a multi-modal deep learning based approach based on CLIP to classify decapod from images, DecapodAI was developed by training the Fine-tuninged Clip model with the images from World Register of Marine Species.
Availability: The DecapodAI is available at www.csbio.sjtu.edu.cn/bioinf/DecapodAI.
Figure 1. The flowchart of the proposed DecapodAI
|
|