Submission code for Atlantic. Please cite if you find it useful!
This repository contains the code for the PlantCLEF 2024 competition submission by ID Atlantic. The task will be evaluated as a multi-label classification task that aims to predict all the plant species present in high-resolution plot images.
The main challenge of this task is the shift between the test data (high-resolution multi-label images of vegetation plots) and the training data (single-label images of individual plants).
The objective is to achieve accurate multi-species plant identification in vegetation plot images. This involves:
- Analyzing high-resolution plot images.
- Predicting multiple plant species present in each image.
Submisson for ID Atlantic The task will be evaluated as a multi-label classification task that aims to predict all the plant species on the high-resolution plot images. The main difficulty of the task lies in the shift between the test data (high-resolution multi-label images of vegetation plots) and the training data (single-label images of individual plants).
multi-species plant identification in vegetation plot images
https://www.imageclef.org/node/315 https://huggingface.co/spaces/BVRA/PlantCLEF2024
Code for Plant Clef2024, implementation for our paper). If you find this code useful in your research, please consider citing
- [Divot in PyTorch]
- Requirements
- Code structure
- Acknowledgement
- [Citation]
Conda was used, config as follows:
pip install -r requirements.txtor for a local installation
pip install --user -r requirements.txtconda create enviroment conda install -c conda-forge pytorch-gpu conda install torchvision
The code structure overview
code-base/
│
├── ./script/sliding_window_inference_pipeline.py - generate database files
├── ./script/sliding_window_to_plantclef_csv.py - Data process
│
│
├── models/ - contains Dino V2 models from Team CLEF 2024
│
│
├── database/
│ ├── test/ - data producted for Image testing
│ └── ResultsALL_XXXXW_YYYYS_ZZZZB.csv- all the database X Window size, Y Slide, Z Border pixels
│
- Baseline created
- Conda env setup with repo
- Test Pytorch Vision Dino V2
- Setup
@inproceedings{PlantCLEF2024,
author = {Stephen Foy and Simon McLoughlin},
title = {Utilizing Dino V2 for Domain Adaptation in Vegetation Plot Analysis},
booktitle = {CLEF 2024: Conference and Labs of the Evaluation Forum},
year = {2024}
}