Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206530006> ?p ?o ?g. }
- W3206530006 abstract "To mitigate the burden of data labeling, we aim at improving data efficiency for both classification and regression setups in deep learning. However, the current focus is on classification problems while rare attention has been paid to deep regression, which usually requires more human effort to labeling. Further, due to the intrinsic difference between categorical and continuous label space, the common intuitions for classification, e.g., cluster assumptions or pseudo labeling strategies, cannot be naturally adapted into deep regression. To this end, we first delved into the existing data-efficient methods in deep learning and found that they either encourage invariance to data stochasticity (e.g., consistency regularization under different augmentations) or model stochasticity (e.g., difference penalty for predictions of models with different dropout). To take the power of both worlds, we propose a novel X-model by simultaneously encouraging the invariance to {data stochasticity} and {model stochasticity}. Further, the X-model plays a minimax game between the feature extractor and task-specific heads to further enhance the invariance to model stochasticity. Extensive experiments verify the superiority of the X-model among various tasks, from a single-value prediction task of age estimation to a dense-value prediction task of keypoint localization, a 2D synthetic, and a 3D realistic dataset, as well as a multi-category object recognition task." @default.
- W3206530006 created "2021-10-25" @default.
- W3206530006 creator A5016830021 @default.
- W3206530006 creator A5019241553 @default.
- W3206530006 creator A5034579434 @default.
- W3206530006 creator A5059586503 @default.
- W3206530006 date "2021-10-09" @default.
- W3206530006 modified "2023-09-27" @default.
- W3206530006 title "X-model: Improving Data Efficiency in Deep Learning with A Minimax Model" @default.
- W3206530006 cites W2048679005 @default.
- W3206530006 cites W2104290444 @default.
- W3206530006 cites W2138621090 @default.
- W3206530006 cites W2145494108 @default.
- W3206530006 cites W2149933564 @default.
- W3206530006 cites W2170938446 @default.
- W3206530006 cites W2187089797 @default.
- W3206530006 cites W2194775991 @default.
- W3206530006 cites W2510725918 @default.
- W3206530006 cites W2588246945 @default.
- W3206530006 cites W2592691248 @default.
- W3206530006 cites W2604472421 @default.
- W3206530006 cites W2753738274 @default.
- W3206530006 cites W2772804149 @default.
- W3206530006 cites W27744225 @default.
- W3206530006 cites W2796779902 @default.
- W3206530006 cites W2798991696 @default.
- W3206530006 cites W2842511635 @default.
- W3206530006 cites W2949517790 @default.
- W3206530006 cites W2963435192 @default.
- W3206530006 cites W2964040467 @default.
- W3206530006 cites W2978426779 @default.
- W3206530006 cites W2989700832 @default.
- W3206530006 cites W2990376402 @default.
- W3206530006 cites W3005680577 @default.
- W3206530006 cites W3015865682 @default.
- W3206530006 cites W3035524453 @default.
- W3206530006 cites W3099570996 @default.
- W3206530006 cites W3100859887 @default.
- W3206530006 cites W3106031848 @default.
- W3206530006 cites W3120044914 @default.
- W3206530006 cites W3167521527 @default.
- W3206530006 cites W3168442901 @default.
- W3206530006 cites W57680428 @default.
- W3206530006 doi "https://doi.org/10.48550/arxiv.2110.04572" @default.
- W3206530006 hasPublicationYear "2021" @default.
- W3206530006 type Work @default.
- W3206530006 sameAs 3206530006 @default.
- W3206530006 citedByCount "0" @default.
- W3206530006 crossrefType "posted-content" @default.
- W3206530006 hasAuthorship W3206530006A5016830021 @default.
- W3206530006 hasAuthorship W3206530006A5019241553 @default.
- W3206530006 hasAuthorship W3206530006A5034579434 @default.
- W3206530006 hasAuthorship W3206530006A5059586503 @default.
- W3206530006 hasBestOaLocation W32065300061 @default.
- W3206530006 hasConcept C105795698 @default.
- W3206530006 hasConcept C108583219 @default.
- W3206530006 hasConcept C119857082 @default.
- W3206530006 hasConcept C126255220 @default.
- W3206530006 hasConcept C136764020 @default.
- W3206530006 hasConcept C149728462 @default.
- W3206530006 hasConcept C153180895 @default.
- W3206530006 hasConcept C154945302 @default.
- W3206530006 hasConcept C162324750 @default.
- W3206530006 hasConcept C187736073 @default.
- W3206530006 hasConcept C2776135515 @default.
- W3206530006 hasConcept C2776436953 @default.
- W3206530006 hasConcept C2780451532 @default.
- W3206530006 hasConcept C33923547 @default.
- W3206530006 hasConcept C37616216 @default.
- W3206530006 hasConcept C41008148 @default.
- W3206530006 hasConcept C5274069 @default.
- W3206530006 hasConcept C83546350 @default.
- W3206530006 hasConceptScore W3206530006C105795698 @default.
- W3206530006 hasConceptScore W3206530006C108583219 @default.
- W3206530006 hasConceptScore W3206530006C119857082 @default.
- W3206530006 hasConceptScore W3206530006C126255220 @default.
- W3206530006 hasConceptScore W3206530006C136764020 @default.
- W3206530006 hasConceptScore W3206530006C149728462 @default.
- W3206530006 hasConceptScore W3206530006C153180895 @default.
- W3206530006 hasConceptScore W3206530006C154945302 @default.
- W3206530006 hasConceptScore W3206530006C162324750 @default.
- W3206530006 hasConceptScore W3206530006C187736073 @default.
- W3206530006 hasConceptScore W3206530006C2776135515 @default.
- W3206530006 hasConceptScore W3206530006C2776436953 @default.
- W3206530006 hasConceptScore W3206530006C2780451532 @default.
- W3206530006 hasConceptScore W3206530006C33923547 @default.
- W3206530006 hasConceptScore W3206530006C37616216 @default.
- W3206530006 hasConceptScore W3206530006C41008148 @default.
- W3206530006 hasConceptScore W3206530006C5274069 @default.
- W3206530006 hasConceptScore W3206530006C83546350 @default.
- W3206530006 hasLocation W32065300061 @default.
- W3206530006 hasOpenAccess W3206530006 @default.
- W3206530006 hasPrimaryLocation W32065300061 @default.
- W3206530006 hasRelatedWork W2779926426 @default.
- W3206530006 hasRelatedWork W4223943233 @default.
- W3206530006 hasRelatedWork W4225161397 @default.
- W3206530006 hasRelatedWork W4283697347 @default.
- W3206530006 hasRelatedWork W4298144215 @default.
- W3206530006 hasRelatedWork W4309045103 @default.
- W3206530006 hasRelatedWork W4312200629 @default.