WeedLiteNet-V2: A Lightweight Residual Multi-Scale CNN with Efficient Channel Attention for Weed Species Classification


Date Published : 16 November 2026

Contributors

Aayush Shrivastava

Lincoln University College, Petaling Jaya, Selangor Darul Ehsan-47301
Author

Dr Ajay Kumar

Lincoln University College, Petaling Jaya, Selangor Darul Ehsan-47301, Malaysia
Author

Keywords

Weed classification; DeepWeeds; lightweight CNN; depthwise-separable convolution; residual learning; multi-scale feature extraction; ECA attention; precision agriculture.

Proceeding

Track

General Track

License

Copyright (c) 2026 Sustainable Global Societies Initiative

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Abstract

The present study reports on the development of WeedLiteNet-V2, a light-weight nine-class weed classifier for DeepWeeds. The model uses depthwise-separable convolution, residual learning, parallel 3x3 and 5x5 depthwise branches, and Efficient Channel Attention (ECA). According to project documentation, the model has 373,839 parameters, achieved a best validation accuracy of 94.97%, and a test accuracy of 94.50% (2,490/2,635). However, these results are preliminary since there was inconsistency in the split count provided, and neither the final checkpoint nor the predicted classes were made available for independent verification.

 

References

No References

Downloads

How to Cite

Shrivastava, A., & Kumar, D. A. . (2026). WeedLiteNet-V2: A Lightweight Residual Multi-Scale CNN with Efficient Channel Attention for Weed Species Classification. Sustainable Global Societies Initiative, 1(15). https://vectmag.com/sgsi/paper/view/1574