摘要：SummaryDeep learning models have become increasingly used for image-based classification. In critical applications such as medical imaging, it is important to convey the reasoning behind the models' decisions in human-understandable forms. In this work, we propose Pyramid Localization Network (PYLON), a deep learning model that delivers precise location explanation by increasing the resolution of heatmaps produced by class activation map (CAM). PYLON substantially improves the quality of CAM’s heatmaps in both general image and medical image domains and excels at pinpointing the locations of small objects. Most importantly, PYLON does not require expert annotation of the object location but instead can be trained using only image-level label. This capability is especially important for domain where expert annotation is often unavailable or costly to obtain. We also demonstrate an effective transfer learning approach for applying PYLON on small datasets and summarize technical guidelines that would facilitate wider adoption of the technique.Graphical abstractDisplay OmittedHighlights•New architecture improves accuracy of heatmaps that explain classification model•Accurately pinpoint small objects, such as nodules in chest radiograph•No pixel-level annotation is required for training•Applicable on small dataset with a two-phase transfer learning approachArtificial intelligence; Computer science; Signal processing
