Virual Oral Presentation Slide by Slide

IEEE/ICACT20230035 Slide.14        [Big Slide]       [YouTube]	Oral Presentation
	High importance weights can make the model pay more attention to the training of these samples. However, to effectively utilize the samples of the low-importance group, the relabeling module compares the maximum predicted probability to the probability of a given label if the maximum predicted probability is higher than the given label with a threshold value. The sample is updated to a new label. So, it can fix the labels of images with low importance weights.

[Go to Next Slide]

Select Voice: Virtual Oral Presentation!!