search

moothes / A2S-v2

A more robust Unsupervised Salient Object Detection (USOD) framework.
MIT License
45 stars 4 forks source link

How to define the hard and easy samples? #1

Open zhuyr97 opened 1 year ago

zhuyr97 commented 1 year ago

I wonder about the gradient visualizations of the different samples. Is it rely on the human to pre-defined?

moothes commented 1 year ago

Hello! Thank for your attention on our work.

There is not a thresholding function to define which samples are hard or easy in our method. We consider the classification scores as confidences for samples. For example, samples with higher confidences are considered easier, and those with lower confidences are considered harder. In addition, the classification scores closer to 0 or 1 are more confident, whereas those closer to 0.5 means lower confidences. Therefore, the hardness of samples will continuously change during training.