데이터셋 품질 개선을 위한 Self-Supervised Vision Transformer 기반의 객체 Pseudo-label 생성 기법 = An Object Pseudo-Label Generation Technique based on Self-Supervised Vision Transformer for Improving Dataset Quality

다국어 초록 (Multilingual Abstract)

Image segmentation is one of the most important tasks. It localizes objects into bounding boxes and classifies pixels in an image. The performance of an Instance segmentation model requires datasets with labels for objects of various sizes. However, the recently released 'Image for Small Object Detection' dataset has large and common objects that lack labels, causing potential performance degradation. In this paper, we improve the quality of datasets by generating pseudo-labels for general objects using an unsupervised learning-based pseudo-labeling methodology to solve the aforementioned problems. Specifically, small object detection performance was improved by (+2.54 AP) compared to the original dataset. Moreover, we were able to prove an increase in performance using only a small amount of data. As a result, it was confirmed that the quality of the dataset was improved through the proposed method.