CBAM-STN-TPS-YOLO: Enhancing Agricultural Object Detection through Spatially Adaptive Attention Mechanisms

TL;DR

This paper introduces CBAM-STN-TPS-YOLO, a novel agricultural object detection model that combines non-rigid spatial transformations and attention mechanisms to improve accuracy in complex, occlusion-heavy scenarios.

Contribution

The paper presents a new model integrating Thin-Plate Splines with Spatial Transformer Networks and CBAM for enhanced non-rigid spatial alignment and feature emphasis in agricultural detection tasks.

Findings

Outperforms previous models in precision, recall, and mAP on PGP dataset

Reduces false positives by 12%

Supports real-time edge deployment

Abstract

Object detection is vital in precision agriculture for plant monitoring, disease detection, and yield estimation. However, models like YOLO struggle with occlusions, irregular structures, and background noise, reducing detection accuracy. While Spatial Transformer Networks (STNs) improve spatial invariance through learned transformations, affine mappings are insufficient for non-rigid deformations such as bent leaves and overlaps. We propose CBAM-STN-TPS-YOLO, a model integrating Thin-Plate Splines (TPS) into STNs for flexible, non-rigid spatial transformations that better align features. Performance is further enhanced by the Convolutional Block Attention Module (CBAM), which suppresses background noise and emphasizes relevant spatial and channel-wise features. On the occlusion-heavy Plant Growth and Phenotyping (PGP) dataset, our model outperforms STN-YOLO in precision, recall, and mAP. It achieves a 12% reduction in false positives, highlighting the benefits of improved spatial flexibility and attention-guided refinement. We also examine the impact of the TPS regularization parameter in balancing transformation smoothness and detection performance. This lightweight model improves spatial awareness and supports real-time edge deployment, making it ideal for smart farming applications requiring accurate and efficient monitoring.