# key-fg DETR based camouflaged locust objects in complex fields

## TL;DR

This paper introduces a new detection framework to better identify camouflaged pests in complex agricultural environments.

## Contribution

A Transformer-based detection framework with three novel modules for improved camouflaged pest detection.

## Key findings

- The model achieves AP scores of 36.31 on COD10k and 75.07 on Locust datasets.
- Recall and F1-score improve by 6.15% and 6.52% on the Locust dataset.
- Ablation studies confirm the effectiveness of each introduced module.

## Abstract

In real agricultural environments, many pests camouflage themselves against complex backgrounds, significantly increasing detection difficulty. This study addresses the challenge of camouflaged pest detection.

We propose a Transformer-based detection framework that integrates three key modules: 1.Fine-Grained Score Predictor (FGSP) – guides object queries to potential foreground regions; 2.MaskMLP generates instance-aware pixel-level masks; 3.Denoising Module and DropKey strategy – enhance training stability and attention robustness.

Evaluated on the COD10k and Locust datasets, our model achieves AP scores of 36.31 and 75.07, respectively, outperforming Deformable DETR by 2.3% and 3.1%. On the Locust dataset, Recall and F1-score improve by 6.15% and 6.52%, respectively. Ablation studies confirm the contribution of each module.

These results demonstrate that our method significantly improves detection of camouflaged pests in complex field environments. It offers a robust solution for agricultural pest monitoring and crop protection applications.