HugoHE/yolov10-voc-finetune

YOLOv10 - Pascal Visual Object Classes (VOC) Vanilla

YOLOv10 model fine-tuned on Pascal VOC dataset to mitigate hallucination on out-of-distribution data for improved general object detection performance.

Model Details

• Model Type: YOLOv10 Object Detection
• Dataset: Pascal Visual Object Classes (VOC)
• Training Method: fine-tuned to mitigate hallucination on out-of-distribution data
• Framework: PyTorch/Ultralytics
• Task: Object Detection

Dataset Information

This model was trained on the Pascal Visual Object Classes (VOC) dataset, which contains the following object classes:

aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, diningtable, dog, horse, motorbike, person, pottedplant, sheep, sofa, train, tvmonitor

Dataset-specific Details:

Pascal Visual Object Classes (VOC) Dataset:

• Standard benchmark dataset for object detection
• Contains 20 object classes representing common objects
• Widely used for evaluating computer vision models
• High-quality annotations with precise bounding boxes

Usage

This model can be used with the Ultralytics YOLOv10 framework:

from ultralytics import YOLO

# Load the model
model = YOLO('path/to/best.pt')

# Run inference
results = model('path/to/image.jpg')

# Process results
for result in results:
    boxes = result.boxes.xyxy   # bounding boxes
    scores = result.boxes.conf  # confidence scores
    classes = result.boxes.cls  # class predictions

Model Performance

This model was fine-tuned to mitigate hallucination on out-of-distribution data on the Pascal Visual Object Classes (VOC) dataset using YOLOv10 architecture.

Fine-tuning Objective: This model was specifically fine-tuned to mitigate hallucination on out-of-distribution (OOD) data, improving robustness when encountering images that differ from the training distribution.

Intended Use

• Primary Use: Object detection in general computer vision applications
• Suitable for: Research, development, and deployment of object detection systems
• Limitations: Performance may vary on images significantly different from the training distribution

Citation

If you use this model, please cite:

@article{yolov10,
  title={YOLOv10: Real-Time End-to-End Object Detection},
  author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang},
  journal={arXiv preprint arXiv:2405.14458},
  year={2024}
}

License

This model is released under the MIT License.

Keywords

YOLOv10, Object Detection, Computer Vision, Pascal-VOC, Autonomous Driving, Deep Learning