Closed csustYyh closed 1 year ago
I excluded the background class when calculating, and I obtained the results(-0.1 ~ -0.25).
In Fig.6, color bands showing the interquartile range, I thought it was mIoU,I misunderstood it. But I still want to know if my way of calculating mIoU is correct.
I am not checking your code but the trend looks correct.
Thanks for your reply, I guess there is no bug.
Do you include the background when calculating mIoU? The results I calculated are somewhat unusual; the decrease in mIoU(-0.07 ~ -0.17) is not as significant as shown in Figure 6(-0.1 ~ -0.4).
I used the original data you provided, 81.5 and 83.1.
About STCN, I used the original data you provided, 83.3(computed with official model without top-k) and 85.3.
Here is my code: