Open tarepanda1024 opened 10 months ago
@rentainhe can you help me or give me some advice ?
@rentainhe can you help me or give me some advice ?
There does appear to be an issue with the control over counterexamples in the Grounding-DINO model. This may be due to the model's weights. It might be worth trying better weights to see if it alleviates such a problem.
@rentainhe can you help me or give me some advice ?
There does appear to be an issue with the control over counterexamples in the Grounding-DINO model. This may be due to the model's weights. It might be worth trying better weights to see if it alleviates such a problem.
Thx, i will try with another model weight.
@rentainhe can you help me or give me some advice ?
There does appear to be an issue with the control over counterexamples in the Grounding-DINO model. This may be due to the model's weights. It might be worth trying better weights to see if it alleviates such a problem.
Sorry, could you please confirm again if you are referring to replacing the model or adjusting the parameters in GroundingDINO_SwinB.cfg.py?
Need i change models blow or adjusting config?
My text prompt is 1cat . photos blow are all recogize failed.
我个人实践,在openset上用Grounding-DINO在上做开放目标检测,有些理解
我个人实践,在openset上用Grounding-DINO在上做开放目标检测,有些理解
- text prompt尽量多测试,并且用地道英语(1cat我都不太能理解),一般框都挺准,但可能和text对不上
- box thresh可以调高些,但text thresh过高会出现断词的现象
- 对于box占全图过大的case就过滤掉
- 加些启发式联合过滤,比如衣服一定有人脸
- openset的zero short 不可避免地会有误检,只能说在大数据范围内准确率还有个60%多,剩下的还得double check
好的,感谢~
输入的prompt为sun /cat/ dog 等。图中圈出来的都有问题:
下面这个是原图: