Year: 2017
Type: conference-paper
Abstract: For deep CNN-based image classification models, we observe that confusions between classes with high visual similarity are much stronger than those where classes are visually dissimilar. With these unbalanced confusions, classes can be organized in communities, which is similar to cliques of people in the social network. Based on this, we propose a graph-based tool named "confusion graph" to quantify these confusions and further reveal the community structure inside the database. With this community structure, we can diagnose the model's weaknesses and improve the classification accuracy using specialized expert sub-nets, which is comparable to other state-of-the-art techniques. Utilizing this community information, we can also employ pre-trained models to automatically identify mislabeled images in the large scale database. With our method, researchers just need to manually check approximate 3% of the ILSVRC2012 classification database to locate almost all mislabeled samples.
Authors: Ruochun Jin, Yong Dou, Yueqing Wang, Xin Niu
Institution: National University of Defense Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Awards: G4633171827, G708539502, G8071958917
OpenAlex ID: W2742055352