Digital Library[ Search Result ]
A Survey of Advantages of Self-Supervised Learning Models in Visual Recognition Tasks
Euihyun Yoon, Hyunjong Lee, Donggeon Kim, Joochan Park, Jinkyu Kim, Jaekoo Lee
http://doi.org/10.5626/JOK.2024.51.7.609
Recently, the field of teacher-based artificial intelligence (AI) has been rapidly advancing. However, teacher-based learning relies on datasets with specified correct answers, which can increase the cost of obtaining these correct answers. To address this issue, self-supervised learning, which can learn general features of photos without needing correct answers, is being researched. In this paper, various self-supervised learning models were classified based on their learning methods and backbone networks. Their strengths, weaknesses, and performances were then compared and analyzed. Photo classification tasks were used for performance comparison. For comparing the performance of transfer learning, detailed prediction tasks were also compared and analyzed. As a result, models that only used positive pairs achieved higher performance by minimizing noise than models that used both positive and negative pairs. Furthermore, for fine-grained predictions, methods such as masking images for learning or utilizing multi-stage models achieved higher performance by additionally learning regional information.
An Object Pseudo-Label Generation Technique based on Self-Supervised Vision Transformer for Improving Dataset Quality
Dohyun Kim, Jiwoong Jeon, Seongtaek Lim, Hongchul Lee
http://doi.org/10.5626/JOK.2024.51.1.49
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.
Interpolation Method for CT Image Reconstruction using Features Inferred by Self-Supervised Learning
http://doi.org/10.5626/JOK.2021.48.9.1007
Since volumetric data includes internal information, it has an advantage of performing quantitative analysis. Especially medical image data render 3D structures of internal organs, and cubic voxel is necessary for accurate visualization. However, CT image volume is acquired in low z-resolution to reduce X-ray dose exposure. Between slices, image interpolation is a necessary step for visualization as well as for 3D data analysis. In this paper, we propose a self-supervised learning algorithm as an interpolation method that uses the information from the high-resolution images to infer missing information between slices. To achieve this, downscaled slice images are given as the input of the network, and the network recovers the original slice images from the downscaled images. The result of our method outperformed the commonly practiced interpolation methods - nearest-neighbor and trilinear interpolation – in the field, with respect to estimating details. Also, we verified that the proposed algorithm performs comparably with the supervised model with the same network.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr