Multi-task learning for dense object detection
Abstract:
Presented herein are systems and methods for feature detection in images. A computing system may identify a biomedical image having features. The computing system may apply the biomedical image to a feature detection model. The feature detection model may include an encoder-decoder block to generate a feature map corresponding to the biomedical image, a confidence map generator having a second set of parameters to generate a confidence map using the feature map, and a localization map generator to generate a localization map using the feature map. The computing system may generate a resultant map based on the confidence map and the localization map. The resultant map identifying one or more points corresponding to the one or more features. The computing system may provide the one or more points identified in the resultant map for the biomedical image.
Public/Granted literature
Information query
Patent Agency Ranking
0/0