Dear @ruotianluo,
Thank you for your work. I have a general question. In the VOC and COCO datasets there are some classes (e.g., 20 or 80 classes (person, car, horse, etc.) for object detection). If one train the network just for one class (e.g., just the person class) will the accuracy (mAP) of person detection increase?
Have you ever try this?
ruotianluo
commented
6 years ago
Dear @ruotianluo, Thank you for your work. I have a general question. In the VOC and COCO datasets there are some classes (e.g., 20 or 80 classes (person, car, horse, etc.) for object detection). If one train the network just for one class (e.g., just the person class) will the accuracy (mAP) of person detection increase? Have you ever try this?