| 研究開始時の研究の概要 |
This research aims to make the computer smarter in semantic segmentation by more and more interaction with humans.
First, we can provide few new data that contain new categories to make the computer able to segment the image regions of new categories. In a simple case, given only one image with its annotation for bananas, the computer able to segment the regions of bananas.
Second, we aim to make the computer able to discover valuable data during running. In this way, the computer can significantly improve its performance by asking humans to annotate few but valuable data.
|
| 研究実績の概要 |
This research aims to improve semantic segmentation through two solutions, including the passive and active solutions. The passive solution provides the computer with a few new annotated data for new categories to make the computer able to segment the image regions of new categories. The active solution makes the computer able to discover valuable data during running and use them to improve the model.
In 2021, we completed the passive solution by proposing a method named Segmentation by Dynamic Prototype (SDP). SDP does segmentation by searching each pixel's features nearest prototype in feature space. A prototype is a representative feature of a class. During running, it is dynamically constructed by a few new annotated data and old data. We submitted this work to a journal, and it is under review so far.
As for the active solution, we proposed a continual active learning method for semantic segmentation. It can continually select informative images to annotate and feed them to the model to improve accuracies. But the improvement is not satisfactory so far, and we will do more research in the next.
Besides, during the research, we found large redundant storage and RAM resources in cloud servers. Thus, we proposed a method named Neural Routing by Memory, which utilizes the redundant resources to improve accuracies. The work was accepted by NeurIPS 2021.
|
