Papers

Basic information

Name ENDO KAZUKI
Belonging department Management Information Course,Department of Business,Faculty of Humanities and Social Sciences
Occupation name Associate Professor
researchmap researcher code
researchmap agency

Title 

CNN-Based Classification of Degraded Images Without Sacrificing Clean Images

					

					

						

							

								

									
Bibliography怀Type 

									
								

							

						

						
Joint Author

					

					

						

							

								

									
Summary 

									
								

							

						

						
This paper proposed multi-task learning for the classification of degraded images and the estimation of degradation levels by using consistency regularization for image features. The results showed that the proposed method was able to classify degraded images without sacrificing the classification performance of clean images.
Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi

					

					

						

							

								

									
Magazine(name) 

									
								

							

						

						
IEEE Access

					

					

						

							

								

									
Date of Issue 

									
								

							

						

						
202108