# WeedSense: Multi-Task Learning for Weed Segmentation, Height Estimation, and Growth Stage Classification

Source: [WeedSense: Multi-Task Learning for Weed Segmentation, Height Estimation, and Growth Stage Classification](<https://www.sota2.com/research/paper/68fa7ab81e209131cea84c77>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:25:52.609Z

Authors: Toqi Tahamid Sarker, Khaled R Ahmed, Taminul Islam, Cristiana Bernardi Rankrape, Karla Gage

Published: 2025-08-20T07:21:52.000Z

## Abstract

Weed management represents a critical challenge in agriculture, significantly impacting crop yields and requiring substantial resources for control. Effective weed monitoring and analysis strategies are crucial for implementing sustainable agricultural practices and site-specific management approaches. We introduce WeedSense, a novel multi-task learning architecture for comprehensive weed analysis that jointly performs semantic segmentation, height estimation, and growth stage classification. We present a unique dataset capturing 16 weed species over an 11-week growth cycle with pixel-level annotations, height measurements, and temporal labels. WeedSense leverages a dual-path encoder incorporating Universal Inverted Bottleneck blocks and a Multi-Task Bifurcated Decoder with transformer-based feature fusion to generate multi-scale features and enable simultaneous prediction across multiple tasks. WeedSense outperforms other state-of-the-art models on our comprehensive evaluation. On our multi-task dataset, WeedSense achieves mIoU of 89.78% for segmentation, 1.67cm MAE for height estimation, and 99.99% accuracy for growth stage classification while maintaining real-time inference at 160 FPS. Our multitask approach achieves 3$\\times$ faster inference than sequential single-task execution and uses 32.4% fewer parameters. Please see our project page at weedsense.github.io.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Weed Segmentation on WeedBananaCOD (test)](<https://www.sota2.com/research/sota/weed-segmentation-on-weedbananacod-test.md>): Weed Segmentation; WeedBananaCOD (test); IoU (Background): 98.6.

- [Semantic Segmentation on WeedMap (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-weedmap-test.md>): Semantic segmentation; WeedMap (test); mIoU: 75.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.14486>)

[PDF](<https://arxiv.org/pdf/2508.14486.pdf>)
