Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311014066> ?p ?o ?g. }
- W4311014066 endingPage "3062" @default.
- W4311014066 startingPage "3041" @default.
- W4311014066 abstract "The application of Deep Neural Networks (DNNs) to a broad variety of tasks demands methods for coping with the complex and opaque nature of these architectures. When a gold standard is available, performance assessment treats the DNN as a black box and computes standard metrics based on the comparison of the predictions with the ground truth. A deeper understanding of performances requires going beyond such evaluation metrics to diagnose the model behavior and the prediction errors. This goal can be pursued in two complementary ways. On one side, model interpretation techniques “open the box” and assess the relationship between the input, the inner layers and the output, so as to identify the architecture modules most likely to cause the performance loss. On the other hand, black-box error diagnosis techniques study the correlation between the model response and some properties of the input not used for training, so as to identify the features of the inputs that make the model fail. Both approaches give hints on how to improve the architecture and/or the training process. This paper focuses on the application of DNNs to computer vision (CV) tasks and presents a survey of the tools that support the black-box performance diagnosis paradigm. It illustrates the features and gaps of the current proposals, discusses the relevant research directions and provides a brief overview of the diagnosis tools in sectors other than CV." @default.
- W4311014066 created "2022-12-22" @default.
- W4311014066 creator A5001321268 @default.
- W4311014066 creator A5024296934 @default.
- W4311014066 creator A5040255765 @default.
- W4311014066 creator A5089019752 @default.
- W4311014066 date "2022-12-10" @default.
- W4311014066 modified "2023-10-06" @default.
- W4311014066 title "Black-box error diagnosis in Deep Neural Networks for computer vision: a survey of tools" @default.
- W4311014066 cites W1507506748 @default.
- W4311014066 cites W1590014818 @default.
- W4311014066 cites W1832500336 @default.
- W4311014066 cites W1861492603 @default.
- W4311014066 cites W1972515067 @default.
- W4311014066 cites W2102539288 @default.
- W4311014066 cites W2107775979 @default.
- W4311014066 cites W2120109270 @default.
- W4311014066 cites W2137406659 @default.
- W4311014066 cites W2295107390 @default.
- W4311014066 cites W2330219538 @default.
- W4311014066 cites W2394669110 @default.
- W4311014066 cites W2512274390 @default.
- W4311014066 cites W2519571209 @default.
- W4311014066 cites W2565516711 @default.
- W4311014066 cites W2657631929 @default.
- W4311014066 cites W2765137706 @default.
- W4311014066 cites W2765793020 @default.
- W4311014066 cites W2794284562 @default.
- W4311014066 cites W2800388963 @default.
- W4311014066 cites W2883915488 @default.
- W4311014066 cites W2886614482 @default.
- W4311014066 cites W2901160118 @default.
- W4311014066 cites W2914016760 @default.
- W4311014066 cites W2944364052 @default.
- W4311014066 cites W2945526235 @default.
- W4311014066 cites W2951323451 @default.
- W4311014066 cites W2958089299 @default.
- W4311014066 cites W2962772482 @default.
- W4311014066 cites W2962850098 @default.
- W4311014066 cites W2962858109 @default.
- W4311014066 cites W2963374347 @default.
- W4311014066 cites W2963707011 @default.
- W4311014066 cites W2963795072 @default.
- W4311014066 cites W2963847595 @default.
- W4311014066 cites W2964118874 @default.
- W4311014066 cites W2964208152 @default.
- W4311014066 cites W2964260135 @default.
- W4311014066 cites W2964303497 @default.
- W4311014066 cites W2972594731 @default.
- W4311014066 cites W2979344246 @default.
- W4311014066 cites W3042781247 @default.
- W4311014066 cites W3042795548 @default.
- W4311014066 cites W3043995050 @default.
- W4311014066 cites W3080876831 @default.
- W4311014066 cites W3081229243 @default.
- W4311014066 cites W3084079971 @default.
- W4311014066 cites W3101662419 @default.
- W4311014066 cites W3103376464 @default.
- W4311014066 cites W3116271762 @default.
- W4311014066 cites W3116286104 @default.
- W4311014066 cites W3119260202 @default.
- W4311014066 cites W3119676385 @default.
- W4311014066 cites W3124372372 @default.
- W4311014066 cites W3125997628 @default.
- W4311014066 cites W3129250023 @default.
- W4311014066 cites W3133787595 @default.
- W4311014066 cites W3134811542 @default.
- W4311014066 cites W3135550350 @default.
- W4311014066 cites W3136745780 @default.
- W4311014066 cites W3154190849 @default.
- W4311014066 cites W3156354433 @default.
- W4311014066 cites W3164768164 @default.
- W4311014066 cites W3181414820 @default.
- W4311014066 cites W3186465901 @default.
- W4311014066 cites W3186608063 @default.
- W4311014066 cites W3208227120 @default.
- W4311014066 cites W3215450491 @default.
- W4311014066 cites W4210487042 @default.
- W4311014066 cites W4210736086 @default.
- W4311014066 cites W4283314639 @default.
- W4311014066 cites W4285357692 @default.
- W4311014066 cites W4292967989 @default.
- W4311014066 doi "https://doi.org/10.1007/s00521-022-08100-9" @default.
- W4311014066 hasPublicationYear "2022" @default.
- W4311014066 type Work @default.
- W4311014066 citedByCount "2" @default.
- W4311014066 countsByYear W43110140662022 @default.
- W4311014066 countsByYear W43110140662023 @default.
- W4311014066 crossrefType "journal-article" @default.
- W4311014066 hasAuthorship W4311014066A5001321268 @default.
- W4311014066 hasAuthorship W4311014066A5024296934 @default.
- W4311014066 hasAuthorship W4311014066A5040255765 @default.
- W4311014066 hasAuthorship W4311014066A5089019752 @default.
- W4311014066 hasBestOaLocation W43110140662 @default.
- W4311014066 hasConcept C108583219 @default.
- W4311014066 hasConcept C111919701 @default.
- W4311014066 hasConcept C113775141 @default.
- W4311014066 hasConcept C119857082 @default.