We retrain the YOLO-series detection framework on the ego-object dataset in order to obtain a more complete egocentric perspective visual tool chain. The backbone for the detecor is from YOLOv5. The ego-object dataset is from the : https://ai.meta.com/datasets/egoobjects-downloads/. In this work, we do not set the object classification branch in YOLO, only the foreground (object) and background were classified.
- We freeze the Classify Decoder and set the classification-head into a binary class structure – front ground and back ground.
- We involve the COCO pretrained backbone and finetune on the Ego-Object Datasets
- Reset all the data into a COCO format from detron2 format.
-
Download the pretrained YOLO: The pretrained model is putted in: https://drive.google.com/drive/folders/1j6z27hA8vNA_oCB8aZcYrNG2JDFEJrlu?usp=drive_link , please download the pretrained model (last.pt or best.pt).
-
Install the package:
pip install -r requirements.txt
-
Run with:
python detect.py --weights best.pt --source $Your Image$
Here is the mAP-50 results without pretrained YOLOv5 and pretrained YOLOv5:
The pretrained results:
![image](https://private-user-images.githubusercontent.com/42260891/272043225-f9c613dd-19cb-424e-a63c-5103ba2f0feb.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.UiaGDA9LCNL1caD9smOmf7Eisqd5mdQi5GlHTEPQg3Y)