Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044803312> ?p ?o ?g. }
- W3044803312 abstract "Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly effective, because supervised learning can never be exhaustive and thus learning autonomously allows to discover invariances and regularities that help to generalize. In this paper we propose to apply a similar approach to the problem of object recognition across domains: our model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals on the same images. This secondary task helps the network to focus on object shapes, learning concepts like spatial orientation and part correlation, while acting as a regularizer for the classification task over multiple visual domains. Extensive experiments confirm our intuition and show that our multi-task method combining supervised and self-supervised knowledge shows competitive results with respect to more complex domain generalization and adaptation solutions. It also proves its potential in the novel and challenging predictive and partial domain adaptation scenarios." @default.
- W3044803312 created "2020-07-29" @default.
- W3044803312 creator A5004857169 @default.
- W3044803312 creator A5005328139 @default.
- W3044803312 creator A5015264075 @default.
- W3044803312 creator A5024757596 @default.
- W3044803312 creator A5073146276 @default.
- W3044803312 creator A5080303732 @default.
- W3044803312 date "2020-07-24" @default.
- W3044803312 modified "2023-09-24" @default.
- W3044803312 title "Self-Supervised Learning Across Domains" @default.
- W3044803312 cites W1576445103 @default.
- W3044803312 cites W1722318740 @default.
- W3044803312 cites W1731081199 @default.
- W3044803312 cites W1822439997 @default.
- W3044803312 cites W1920962657 @default.
- W3044803312 cites W1958236864 @default.
- W3044803312 cites W2031342017 @default.
- W3044803312 cites W2099471712 @default.
- W3044803312 cites W2104094955 @default.
- W3044803312 cites W2108598243 @default.
- W3044803312 cites W2112796928 @default.
- W3044803312 cites W2148349024 @default.
- W3044803312 cites W2155858138 @default.
- W3044803312 cites W2159291411 @default.
- W3044803312 cites W219040644 @default.
- W3044803312 cites W2295107390 @default.
- W3044803312 cites W2321533354 @default.
- W3044803312 cites W2326925005 @default.
- W3044803312 cites W2335728318 @default.
- W3044803312 cites W2342877626 @default.
- W3044803312 cites W2426687555 @default.
- W3044803312 cites W2511131004 @default.
- W3044803312 cites W2617027347 @default.
- W3044803312 cites W2750549109 @default.
- W3044803312 cites W2758584002 @default.
- W3044803312 cites W2763549966 @default.
- W3044803312 cites W2768591600 @default.
- W3044803312 cites W2769112066 @default.
- W3044803312 cites W2782016767 @default.
- W3044803312 cites W2792501240 @default.
- W3044803312 cites W2798593490 @default.
- W3044803312 cites W2798658180 @default.
- W3044803312 cites W2799084346 @default.
- W3044803312 cites W2883725317 @default.
- W3044803312 cites W2885722640 @default.
- W3044803312 cites W2889965839 @default.
- W3044803312 cites W2894728917 @default.
- W3044803312 cites W2895478406 @default.
- W3044803312 cites W2903918135 @default.
- W3044803312 cites W2913340405 @default.
- W3044803312 cites W2913620370 @default.
- W3044803312 cites W2922035427 @default.
- W3044803312 cites W2922499403 @default.
- W3044803312 cites W2926393255 @default.
- W3044803312 cites W2936604471 @default.
- W3044803312 cites W2947707615 @default.
- W3044803312 cites W2949436635 @default.
- W3044803312 cites W2949987290 @default.
- W3044803312 cites W2951111165 @default.
- W3044803312 cites W2962687275 @default.
- W3044803312 cites W2962742544 @default.
- W3044803312 cites W2962808524 @default.
- W3044803312 cites W2962824366 @default.
- W3044803312 cites W2962935454 @default.
- W3044803312 cites W2962960500 @default.
- W3044803312 cites W2962986791 @default.
- W3044803312 cites W2963003918 @default.
- W3044803312 cites W2963043696 @default.
- W3044803312 cites W2963118547 @default.
- W3044803312 cites W2963870446 @default.
- W3044803312 cites W2964109570 @default.
- W3044803312 cites W2964278684 @default.
- W3044803312 cites W2964288524 @default.
- W3044803312 cites W2964314879 @default.
- W3044803312 cites W2968095426 @default.
- W3044803312 cites W2970018230 @default.
- W3044803312 cites W2970119729 @default.
- W3044803312 cites W2971581398 @default.
- W3044803312 cites W2982204955 @default.
- W3044803312 cites W2995489995 @default.
- W3044803312 cites W2998653622 @default.
- W3044803312 cites W2998712190 @default.
- W3044803312 cites W3000097396 @default.
- W3044803312 cites W3008503415 @default.
- W3044803312 cites W3014493675 @default.
- W3044803312 cites W3015272069 @default.
- W3044803312 cites W3016742313 @default.
- W3044803312 cites W3023371261 @default.
- W3044803312 cites W3026042427 @default.
- W3044803312 cites W3034559532 @default.
- W3044803312 cites W3035219538 @default.
- W3044803312 cites W3109093849 @default.
- W3044803312 cites W3121432811 @default.
- W3044803312 cites W572186939 @default.
- W3044803312 hasPublicationYear "2020" @default.
- W3044803312 type Work @default.
- W3044803312 sameAs 3044803312 @default.
- W3044803312 citedByCount "1" @default.
- W3044803312 countsByYear W30448033122021 @default.