A workflow diagram of our pipeline, showing the classification, localization, and segmentation mask prediction steps. The DM-time transform acts as an input to the algorithm. Feature maps are obtained using a backbone CNN, which are upsampled by the FPN to obtain high semantics across different scales. The RPN proposes regions of interest across the image where relevant objects may be present, performing a light-weight classification. Regions with the highest score are selected and aligned with the original feature map by the RoI Align network. From these RoI, a segmentation mask is obtained through a CNN with an upsampling layer at the end, and a classification score and bounding box coordinates are obtained through a series of fully connected layers, producing the output of the algorithm.
Published in #RASTI RAS Techniques & Instruments: "Enhancing fast radio transient detection with Mask R-CNN image segmentation", Belmonte Díaz et al. This is Fig. 5: please visit academic.oup.com/rasti/articl... to read the paper. @royalastrosoc.bsky.social @academic.oup.com