# RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity

Source: [RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity](<https://www.sota2.com/research/paper/68fa781a1e209131cea76ccf>)

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

Data updated: 2025-10-26T04:32:25.977Z

Authors: Ranjan Sapkota, Rahul Harsha Cheppally, Ajay Sharda, Manoj Karkee

Published: 2025-04-17T17:08:11.000Z

## Abstract

This study conducts a detailed comparison of RF-DETR object detection base model and YOLOv12 object detection model configurations for detecting greenfruits in a complex orchard environment marked by label ambiguity, occlusions, and background blending. A custom dataset was developed featuring both single-class (greenfruit) and multi-class (occluded and non-occluded greenfruits) annotations to assess model performance under dynamic real-world conditions. RF-DETR object detection model, utilizing a DINOv2 backbone and deformable attention, excelled in global context modeling, effectively identifying partially occluded or ambiguous greenfruits. In contrast, YOLOv12 leveraged CNN-based attention for enhanced local feature extraction, optimizing it for computational efficiency and edge deployment. RF-DETR achieved the highest mean Average Precision (mAP50) of 0.9464 in single-class detection, proving its superior ability to localize greenfruits in cluttered scenes. Although YOLOv12N recorded the highest mAP@50:95 of 0.7620, RF-DETR consistently outperformed in complex spatial scenarios. For multi-class detection, RF-DETR led with an mAP@50 of 0.8298, showing its capability to differentiate between occluded and non-occluded fruits, while YOLOv12L scored highest in mAP@50:95 with 0.6622, indicating better classification in detailed occlusion contexts. Training dynamics analysis highlighted RF-DETR's swift convergence, particularly in single-class settings where it plateaued within 10 epochs, demonstrating the efficiency of transformer-based architectures in adapting to dynamic visual data. These findings validate RF-DETR's effectiveness for precision agricultural applications, with YOLOv12 suited for fast-response scenarios. \>Index Terms: RF-DETR object detection, YOLOv12, YOLOv13, YOLOv14, YOLOv15, YOLOE, YOLO World, YOLO, You Only Look Once, Roboflow, Detection Transformers, CNNs

## 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.

- [Industrial Hazard Detection on Public Dataset SynSpill](<https://www.sota2.com/research/sota/industrial-hazard-detection-on-public-dataset-synspill.md>): Industrial Hazard Detection; Public Dataset SynSpill; mAP@50: 83.

- [Industrial Hazard Detection on Proprietary Dataset](<https://www.sota2.com/research/sota/industrial-hazard-detection-on-proprietary-dataset.md>): Industrial Hazard Detection; Proprietary Dataset; mAP@50: 67.

- [Object Detection on Ground-level urban tree detection dataset](<https://www.sota2.com/research/sota/object-detection-on-ground-level-urban-tree-detection-dataset.md>): Object Detection; Ground-level urban tree detection dataset; Precision: 81.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.13099>)

[PDF](<https://arxiv.org/pdf/2504.13099.pdf>)