Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048021811> ?p ?o ?g. }
- W3048021811 endingPage "1316" @default.
- W3048021811 startingPage "1316" @default.
- W3048021811 abstract "Colorectal cancer is one of the leading cancer death causes worldwide, but its early diagnosis highly improves the survival rates. The success of deep learning has also benefited this clinical field. When training a deep learning model, it is optimized based on the selected loss function. In this work, we consider two networks (U-Net and LinkNet) and two backbones (VGG-16 and Densnet121). We analyzed the influence of seven loss functions and used a principal component analysis (PCA) to determine whether the PCA-based decomposition allows for the defining of the coefficients of a non-redundant primal loss function that can outperform the individual loss functions and different linear combinations. The eigenloss is defined as a linear combination of the individual losses using the elements of the eigenvector as coefficients. Empirical results show that the proposed eigenloss improves the general performance of individual loss functions and outperforms other linear combinations when Linknet is used, showing potential for its application in polyp segmentation problems." @default.
- W3048021811 created "2020-08-13" @default.
- W3048021811 creator A5040325942 @default.
- W3048021811 creator A5048902031 @default.
- W3048021811 creator A5061242492 @default.
- W3048021811 creator A5064457618 @default.
- W3048021811 creator A5070871906 @default.
- W3048021811 creator A5077442010 @default.
- W3048021811 date "2020-08-07" @default.
- W3048021811 modified "2023-10-11" @default.
- W3048021811 title "Eigenloss: Combined PCA-Based Loss Function for Polyp Segmentation" @default.
- W3048021811 cites W1909740415 @default.
- W3048021811 cites W1985964670 @default.
- W3048021811 cites W1987869189 @default.
- W3048021811 cites W2008359794 @default.
- W3048021811 cites W2034269173 @default.
- W3048021811 cites W2059975159 @default.
- W3048021811 cites W2078614173 @default.
- W3048021811 cites W2092437977 @default.
- W3048021811 cites W2113464037 @default.
- W3048021811 cites W2123402141 @default.
- W3048021811 cites W2146302903 @default.
- W3048021811 cites W2412782625 @default.
- W3048021811 cites W2560311620 @default.
- W3048021811 cites W2560328367 @default.
- W3048021811 cites W2586952804 @default.
- W3048021811 cites W2592603952 @default.
- W3048021811 cites W2602151200 @default.
- W3048021811 cites W2766166720 @default.
- W3048021811 cites W2792767783 @default.
- W3048021811 cites W2795587607 @default.
- W3048021811 cites W2840687963 @default.
- W3048021811 cites W2902154261 @default.
- W3048021811 cites W2905338897 @default.
- W3048021811 cites W2905617204 @default.
- W3048021811 cites W2912989244 @default.
- W3048021811 cites W2914806156 @default.
- W3048021811 cites W2962162024 @default.
- W3048021811 cites W2962731543 @default.
- W3048021811 cites W2962767316 @default.
- W3048021811 cites W2962914239 @default.
- W3048021811 cites W2963351448 @default.
- W3048021811 cites W2963446712 @default.
- W3048021811 cites W2964098128 @default.
- W3048021811 cites W2969932412 @default.
- W3048021811 cites W2971013993 @default.
- W3048021811 cites W2972417230 @default.
- W3048021811 cites W2976398475 @default.
- W3048021811 cites W2977841542 @default.
- W3048021811 cites W2979524736 @default.
- W3048021811 cites W2979972335 @default.
- W3048021811 cites W2981689412 @default.
- W3048021811 cites W2982207683 @default.
- W3048021811 cites W2988321605 @default.
- W3048021811 cites W2996955463 @default.
- W3048021811 cites W2998215684 @default.
- W3048021811 cites W2999417355 @default.
- W3048021811 cites W3002325867 @default.
- W3048021811 cites W3005311408 @default.
- W3048021811 cites W3005451155 @default.
- W3048021811 cites W3011143880 @default.
- W3048021811 cites W3013184758 @default.
- W3048021811 cites W3013681994 @default.
- W3048021811 cites W3016066905 @default.
- W3048021811 cites W3017134152 @default.
- W3048021811 cites W3019872864 @default.
- W3048021811 cites W3023022915 @default.
- W3048021811 cites W3039728372 @default.
- W3048021811 cites W3046792513 @default.
- W3048021811 cites W3105636206 @default.
- W3048021811 doi "https://doi.org/10.3390/math8081316" @default.
- W3048021811 hasPublicationYear "2020" @default.
- W3048021811 type Work @default.
- W3048021811 sameAs 3048021811 @default.
- W3048021811 citedByCount "12" @default.
- W3048021811 countsByYear W30480218112020 @default.
- W3048021811 countsByYear W30480218112021 @default.
- W3048021811 countsByYear W30480218112022 @default.
- W3048021811 countsByYear W30480218112023 @default.
- W3048021811 crossrefType "journal-article" @default.
- W3048021811 hasAuthorship W3048021811A5040325942 @default.
- W3048021811 hasAuthorship W3048021811A5048902031 @default.
- W3048021811 hasAuthorship W3048021811A5061242492 @default.
- W3048021811 hasAuthorship W3048021811A5064457618 @default.
- W3048021811 hasAuthorship W3048021811A5070871906 @default.
- W3048021811 hasAuthorship W3048021811A5077442010 @default.
- W3048021811 hasBestOaLocation W30480218111 @default.
- W3048021811 hasConcept C104317684 @default.
- W3048021811 hasConcept C105951970 @default.
- W3048021811 hasConcept C108583219 @default.
- W3048021811 hasConcept C11413529 @default.
- W3048021811 hasConcept C121332964 @default.
- W3048021811 hasConcept C127716648 @default.
- W3048021811 hasConcept C14036430 @default.
- W3048021811 hasConcept C153180895 @default.
- W3048021811 hasConcept C154945302 @default.
- W3048021811 hasConcept C158693339 @default.
- W3048021811 hasConcept C185592680 @default.