Figure 3 - uploaded by Wenhao Zheng
Content may be subject to copyright.
Source publication
Image ordinal regression has been mainly studied along the line of exploiting the order of categories. However, the issues of class imbalance and category overlap that are very common in ordinal regression were largely overlooked. As a result, the performance on minority categories is often unsatisfactory. In this paper, we propose a novel framewor...
Contexts in source publication
Context 1
... shown in Fig. 3, in UNet, the concatenated feature map F sf and the last feature map F (4) m of X m are first input into an up-sampling block. This up-sampling process is repeated three times to generate X f . In the repetitions, the concatenated feature map is replaced by the output of the previous block. In the light-weight MAE decoder, a single ...
Context 2
... shown in Fig. 3, in UNet, the concatenated feature map F sf and the last feature map F (4) m of X m are first input into an up-sampling block. This up-sampling process is repeated three times to generate X f . In the repetitions, the concatenated feature map is replaced by the output of the previous block. In the light-weight MAE decoder, a single ...
Similar publications
Image ordinal regression has been mainly studied along the line of exploiting the order of categories. However, the issues of class imbalance and category overlap that are very common in ordinal regression were largely overlooked. As a result, the performance on minority categories is often unsatisfactory. In this paper, we propose a novel framewor...
