Year: 2023
Type: article
Abstract: improvement). SoftOtsuNet is only required at training time, meaning inference costs are unchanged from the baseline. This further suggests that even large data-driven models can still benefit from human-engineered unsupervised loss functions.
Source: PubMed Central
Authors: Miguel Dominguez, John T Finnell
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4390889307
