Reduction of Class Activation Uncertainty with Background Information

arXiv:2305.03238v4 Announce Type: replace
Abstract: Multitask learning is a popular approach to training high-performing neural networks with improved generalization. In this paper, we propose a background class to achieve improved generalization at a lower computation compared to multitask learning to help researchers and organizations with limited computation power. We also present a methodology for selecting background images and discuss potential future improvements. We apply our approach to several datasets and achieve improved generalization with much lower computation. Through the class …

abstract arxiv class computation cs.cv information multitask learning networks neural networks organizations paper popular power researchers training type uncertainty