| --- |
| license: apache-2.0 |
| extra_gated_prompt: >- |
|
|
| |
|
|
| **VehicleNet-RFDETR-s** is a multi-vehicle detection model released under the |
| Apache License, Version 2.0. Access to this model is granted exclusively to |
| individuals who meet the legal age requirements of their jurisdiction and possess |
| the authority to accept and comply with the terms set forth herein. |
|
|
| By requesting access, downloading, or using VehicleNet-RFDETR-s in any capacity, |
| you represent and warrant that: |
|
|
| 1. You satisfy the minimum legal age requirements applicable in your country or region. |
| 2. You are duly authorized to enter into and be bound by this agreement. |
| 3. You will use this model strictly in accordance with the Apache License 2.0 and all |
| applicable local, national, and international laws and regulations. |
|
|
| **Disclaimer of Warranties:** VehicleNet-RFDETR-s is provided "as-is," without |
| warranties of any kind, whether express or implied, including but not limited to |
| warranties of accuracy, reliability, fitness for a particular purpose, or suitability |
| for deployment in safety-critical or regulated environments. The authors and affiliated |
| institutions assume no liability for any direct, indirect, incidental, or consequential |
| damages arising from the use or misuse of this model. |
|
|
| **User Responsibility:** You bear sole responsibility for all use of this model and its |
| outputs. Deployment in production systems, safety-critical applications, or any context |
| without adequate validation and human oversight is strongly discouraged. Any unlawful, |
| unethical, or unauthorized application of this model is strictly prohibited. |
|
|
| If you do not agree to these terms, or if you lack the authority to accept them, |
| you must refrain from accessing or using this model. |
|
|
| extra_gated_fields: |
| First Name: text |
| Last Name: text |
| Country: country |
| Job title: |
| type: select |
| options: |
| - Undergraduate Student |
| - Research Graduate |
| - AI Researcher |
| - AI Developer / Engineer |
| - Other |
| geo: ip_location |
| By submitting an access request, I acknowledge and accept the terms above: checkbox |
| extra_gated_button_content: Submit Access Request |
|
|
| library_name: roboflow |
| tags: |
| - safetensors |
| - roboflow |
| - data-annotation |
| - transformers |
| tensor_type: |
| - F32 |
| - BF16 |
| - F8_E4M3 |
| datasets: |
| - iisc-aim/UVH-26 |
| language: |
| - en |
| metrics: |
| - accuracy |
| - precision |
| - recall |
| - f1 |
| base_model: |
| - qualcomm/RF-DETR |
| pipeline_tag: object-detection |
| --- |
| |
| # VehicleNet-RFDETR-s |
|
|
|  |
|
|
| <a href="https://www.apache.org/licenses/LICENSE-2.0"> |
| <img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="Apache 2.0 License"> |
| </a> |
| <a href="https://github.com/ultralytics/ultralytics"> |
| <img src="https://img.shields.io/badge/RFDETR-Small-red?logo=ultralytics&logoColor=white" alt="RFDETRSmall"> |
| </a> |
| <a href="#performance-metrics"> |
| <img src="https://img.shields.io/badge/mAP%4050:95-0.60555-darkgreen?style=flat" alt="mAP@50:95"> |
| </a> |
|
|
| ## Overview |
|
|
| **VehicleNet-RFDETR-s** is a multi-class vehicle detection model designed for fine-grained vehicle type recognition in real-world traffic scenes. It is fine-tuned on the **UVH-26-MV Dataset**, curated and released by the **Indian Institute of Science (IISc), Bangalore**, which captures the highly complex, dense, and heterogeneous nature of Indian road traffic. |
|
|
| The model recognizes **14 vehicle categories**, including hatchbacks, sedans, SUVs, MUVs, two-wheelers, three-wheelers, buses, trucks, and a range of commercial vehicle types. This **small variant** is optimized for low-latency inference, balancing speed and accuracy for deployment on resource-constrained hardware. |
|
|
| The model is fine-tuned on the **RFDETRSmall** architecture ([arXiv: 2511.09554](https://arxiv.org/pdf/2511.09554)) by Roboflow, using `rfdetr` version 1.6.1. |
|
|
|  |
|
|
|
|
| ## Model Specifications |
|
|
| | Parameter | Value | |
| |-----------------------------|------------------------------| |
| | Base Architecture | RFDETRSmall | |
| | Number of Classes | 14 | |
| | Total Layers | - | |
| | Parameters | 32.1 M | |
| | GFLOPs | - | |
| | Input Resolution | 512 × 512 | |
| | Training Epochs | 10 | |
| | Batch Size | 4 | |
| | Gradient Accumulation Steps | 2 | |
| | Effective Batch Size | 16 *(batch × grad_accum × GPUs)* | |
| | Training Hardware | Dual NVIDIA Tesla T4 GPUs | |
| | Framework | Roboflow (PyTorch) | |
| | Pretrained Weights | RFDETRSmall (Roboflow) | |
|
|
| ## Performance Metrics |
|
|
| | Metric | Value | |
| |--------------|---------| |
| | mAP@50 | 0.71669 | |
| | mAP@50:95 | 0.60555 | |
| | mAP@75 | 0.66804 | |
| | Precision | 0.68535 | |
| | Recall | 0.6889 | |
|
|
| ### Training Curves |
|
|
|  |
|
|
| ## Intended Use |
|
|
| VehicleNet-RFDETR-s is suitable for the following applications: |
|
|
| - **Traffic Surveillance & Analytics** — Automated vehicle classification in urban and highway environments. |
| - **Edge Device Deployment** — Optimized for low-latency inference on constrained hardware. |
| - **Academic Research & Benchmarking** — Evaluation of fine-grained vehicle detection in heterogeneous traffic conditions, particularly on Indian road datasets. |
|
|
| ### Out-of-Scope Use |
|
|
| - Deployment in safety-critical systems without independent validation. |
| - Surveillance applications that violate individual privacy rights or applicable regulations. |
| - Any use case inconsistent with the Apache License 2.0 terms. |
|
|
| ## Citation |
|
|
| If you use this model or the UVH-26-MV dataset in your research, please cite the respective dataset and model sources appropriately. |
|
|
| ## License |
|
|
| This model is released under the **[Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)**. You are free to use, modify, and distribute this model subject to the terms of the license. See the `LICENSE` file for full details. |
