Fig. 3
From: Siamese network with change awareness for surface defect segmentation in complex backgrounds
The basic modules. (a) The sequence reduction attention utilizes the spatial reduction layer to reduce the complexity of the self-attention module from \(O(N^2)\) to \(O\left( \frac{N^2}{R}\right)\). (b) The change-aware decoder, based on a 3-dimensional (horizontal, vertical, and depth) attention module, utilizes the DistMap carrying change information in different ways when detecting objects in fully-supervised and semi-supervised settings.
