FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989590131> ?p ?o ?g. }

• W2989590131 endingPage "203" @default.
• W2989590131 startingPage "196" @default.
• W2989590131 abstract "We present the results of recent challenges in Automated Computer Vision (AutoCV, renamed here for clarity AutoCV1 and AutoCV2, 2019), which are part of a series of challenge on Automated Deep Learning (AutoDL). These two competitions aim at searching for fully automated solutions for classification tasks in computer vision, with an emphasis on any-time performance. The first competition was limited to image classification while the second one included both images and videos. Our design imposed to the participants to submit their code on a challenge platform for blind testing on five datasets, both for training and testing, without any human intervention whatsoever. Winning solutions adopted deep learning techniques based on already published architectures, such as AutoAugment, MobileNet and ResNet, to reach state-of-the-art performance in the time budget of the challenge (only 20 minutes of GPU time). The novel contributions include strategies to deliver good preliminary results at any time during the learning process, such that a method can be stopped early and still deliver good performance. This feature is key for the adoption of such techniques by data analysts desiring to obtain rapidly preliminary results on large datasets and to speed up the development process. The soundness of our design was verified in several aspects: (1) Little overfitting of the on-line leaderboard providing feedback on 5 development datasets was observed, compared to the final blind testing on the 5 (separate) final test datasets, suggesting that winning solutions might generalize to other computer vision classification tasks; (2) Error bars on the winners’ performance allow us to say with confident that they performed significantly better than the baseline solutions we provided; (3) The ranking of participants according to the any-time metric we designed, namely the Area under the Learning Curve, was different from that of the fixed-time metric, i.e. AUC at the end of the fixed time budget. We released all winning solutions under open-source licenses. At the end of the AutoDL challenge series, all data of the challenge will be made publicly available, thus providing a collection of uniformly formatted datasets, which can serve to conduct further research, particularly on meta-learning." @default.
• W2989590131 created "2019-12-05" @default.
• W2989590131 creator A5006360335 @default.
• W2989590131 creator A5023291208 @default.
• W2989590131 creator A5031282560 @default.
• W2989590131 creator A5032604295 @default.
• W2989590131 creator A5037839477 @default.
• W2989590131 creator A5038228433 @default.
• W2989590131 creator A5039824546 @default.
• W2989590131 creator A5066103173 @default.
• W2989590131 creator A5080573113 @default.
• W2989590131 date "2020-07-01" @default.
• W2989590131 modified "2023-10-14" @default.
• W2989590131 title "Towards automated computer vision: analysis of the AutoCV challenges 2019" @default.
• W2989590131 cites W2949736877 @default.
• W2989590131 doi "https://doi.org/10.1016/j.patrec.2020.04.030" @default.
• W2989590131 hasPublicationYear "2020" @default.
• W2989590131 type Work @default.
• W2989590131 sameAs 2989590131 @default.
• W2989590131 citedByCount "5" @default.
• W2989590131 countsByYear W29895901312021 @default.
• W2989590131 countsByYear W29895901312022 @default.
• W2989590131 crossrefType "journal-article" @default.
• W2989590131 hasAuthorship W2989590131A5006360335 @default.
• W2989590131 hasAuthorship W2989590131A5023291208 @default.
• W2989590131 hasAuthorship W2989590131A5031282560 @default.
• W2989590131 hasAuthorship W2989590131A5032604295 @default.
• W2989590131 hasAuthorship W2989590131A5037839477 @default.
• W2989590131 hasAuthorship W2989590131A5038228433 @default.
• W2989590131 hasAuthorship W2989590131A5039824546 @default.
• W2989590131 hasAuthorship W2989590131A5066103173 @default.
• W2989590131 hasAuthorship W2989590131A5080573113 @default.
• W2989590131 hasBestOaLocation W29895901311 @default.
• W2989590131 hasConcept C108583219 @default.
• W2989590131 hasConcept C111919701 @default.
• W2989590131 hasConcept C119857082 @default.
• W2989590131 hasConcept C138885662 @default.
• W2989590131 hasConcept C154945302 @default.
• W2989590131 hasConcept C22019652 @default.
• W2989590131 hasConcept C2776401178 @default.
• W2989590131 hasConcept C41008148 @default.
• W2989590131 hasConcept C41895202 @default.
• W2989590131 hasConcept C50644808 @default.
• W2989590131 hasConcept C98045186 @default.
• W2989590131 hasConceptScore W2989590131C108583219 @default.
• W2989590131 hasConceptScore W2989590131C111919701 @default.
• W2989590131 hasConceptScore W2989590131C119857082 @default.
• W2989590131 hasConceptScore W2989590131C138885662 @default.
• W2989590131 hasConceptScore W2989590131C154945302 @default.
• W2989590131 hasConceptScore W2989590131C22019652 @default.
• W2989590131 hasConceptScore W2989590131C2776401178 @default.
• W2989590131 hasConceptScore W2989590131C41008148 @default.
• W2989590131 hasConceptScore W2989590131C41895202 @default.
• W2989590131 hasConceptScore W2989590131C50644808 @default.
• W2989590131 hasConceptScore W2989590131C98045186 @default.
• W2989590131 hasLocation W29895901311 @default.
• W2989590131 hasLocation W29895901312 @default.
• W2989590131 hasLocation W29895901313 @default.
• W2989590131 hasLocation W29895901314 @default.
• W2989590131 hasOpenAccess W2989590131 @default.
• W2989590131 hasPrimaryLocation W29895901311 @default.
• W2989590131 hasRelatedWork W1574414179 @default.
• W2989590131 hasRelatedWork W2071659704 @default.
• W2989590131 hasRelatedWork W2186333919 @default.
• W2989590131 hasRelatedWork W2989932438 @default.
• W2989590131 hasRelatedWork W3099765033 @default.
• W2989590131 hasRelatedWork W4281702477 @default.
• W2989590131 hasRelatedWork W4297676672 @default.
• W2989590131 hasRelatedWork W4362597605 @default.
• W2989590131 hasRelatedWork W4380075502 @default.
• W2989590131 hasRelatedWork W4387297750 @default.
• W2989590131 hasVolume "135" @default.
• W2989590131 isParatext "false" @default.
• W2989590131 isRetracted "false" @default.
• W2989590131 magId "2989590131" @default.
• W2989590131 workType "article" @default.