This study examined the improvement of microscopy segmentation intersection over union accuracy by transfer learning from a large dataset of microscopy images called MicroNet.Many neural network encoder architectures ...This study examined the improvement of microscopy segmentation intersection over union accuracy by transfer learning from a large dataset of microscopy images called MicroNet.Many neural network encoder architectures were trained on over 100,000 labeled microscopy images from 54 material classes.These pre-trained encoders were then embedded into multiple segmentation architectures including UNet and DeepLabV3+to evaluate segmentation performance on created benchmark microscopy datasets.Compared to ImageNet pre-training,models pre-trained on MicroNet generalized better to out-of-distribution micrographs taken under different imaging and sample conditions and were more accurate with less training data.When training with only a single Ni-superalloy image,pre-training on MicroNet produced a 72.2%reduction in relative intersection over union error.These results suggest that transfer learning from large in-domain datasets generate models with learned feature representations that are more useful for downstream tasks and will likely improve any microscopy image analysis technique that can leverage pre-trained encoders.展开更多
基金This work was supported by the NASA Transformational Tools and Technologies(TTT)project under the Transformative Aeronautics Concept Program within the Aeronautics Research Mission Directorate.
文摘This study examined the improvement of microscopy segmentation intersection over union accuracy by transfer learning from a large dataset of microscopy images called MicroNet.Many neural network encoder architectures were trained on over 100,000 labeled microscopy images from 54 material classes.These pre-trained encoders were then embedded into multiple segmentation architectures including UNet and DeepLabV3+to evaluate segmentation performance on created benchmark microscopy datasets.Compared to ImageNet pre-training,models pre-trained on MicroNet generalized better to out-of-distribution micrographs taken under different imaging and sample conditions and were more accurate with less training data.When training with only a single Ni-superalloy image,pre-training on MicroNet produced a 72.2%reduction in relative intersection over union error.These results suggest that transfer learning from large in-domain datasets generate models with learned feature representations that are more useful for downstream tasks and will likely improve any microscopy image analysis technique that can leverage pre-trained encoders.
