FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2968706510> ?p ?o ?g. }

• W2968706510 abstract "Image recognition is an important topic in computer vision and image processing, and has been mainly addressed by supervised deep learning methods, which need a large set of labeled images to achieve promising performance. However, in most cases, labeled data are expensive or even impossible to obtain, while unlabeled data are readily available from numerous free on-line resources and have been exploited to improve the performance of deep neural networks. To better exploit the power of unlabeled data for image recognition, in this paper, we propose a semi-supervised and generative approach, namely the semi-supervised self-growing generative adversarial network (SGGAN). Label inference is a key step for the success of semi-supervised learning approaches. There are two main problems in label inference: how to measure the confidence of the unlabeled data and how to generalize the classifier. We address these two problems via the generative framework and a novel convolution-block-transformation technique, respectively. To stabilize and speed up the training process of SGGAN, we employ the metric Maximum Mean Discrepancy as the feature matching objective function and achieve larger gain than the standard semi-supervised GANs (SSGANs), narrowing the gap to the supervised methods. Experiments on several benchmark datasets show the effectiveness of the proposed SGGAN on image recognition and facial attribute recognition tasks. By using the training data with only 4% labeled facial attributes, the SGGAN approach can achieve comparable accuracy with leading supervised deep learning methods with all labeled facial attributes." @default.
• W2968706510 created "2019-08-22" @default.
• W2968706510 creator A5006832020 @default.
• W2968706510 creator A5028229824 @default.
• W2968706510 creator A5032806437 @default.
• W2968706510 creator A5042967567 @default.
• W2968706510 creator A5059454224 @default.
• W2968706510 creator A5080722708 @default.
• W2968706510 date "2019-08-11" @default.
• W2968706510 modified "2023-10-16" @default.
• W2968706510 title "Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition" @default.
• W2968706510 cites W1555194058 @default.
• W2968706510 cites W1572063013 @default.
• W2968706510 cites W1596717185 @default.
• W2968706510 cites W1599238028 @default.
• W2968706510 cites W1782590233 @default.
• W2968706510 cites W1834627138 @default.
• W2968706510 cites W1921523184 @default.
• W2968706510 cites W1990334093 @default.
• W2968706510 cites W1998709268 @default.
• W2968706510 cites W2035813998 @default.
• W2968706510 cites W2079349076 @default.
• W2968706510 cites W2097117768 @default.
• W2968706510 cites W2099471712 @default.
• W2968706510 cites W2108501770 @default.
• W2968706510 cites W2108598243 @default.
• W2968706510 cites W2112796928 @default.
• W2968706510 cites W2118696714 @default.
• W2968706510 cites W2126448884 @default.
• W2968706510 cites W2128560777 @default.
• W2968706510 cites W2147414309 @default.
• W2968706510 cites W2163605009 @default.
• W2968706510 cites W2170973209 @default.
• W2968706510 cites W2178768799 @default.
• W2968706510 cites W2194775991 @default.
• W2968706510 cites W2207282238 @default.
• W2968706510 cites W2212660284 @default.
• W2968706510 cites W2280377497 @default.
• W2968706510 cites W2311523351 @default.
• W2968706510 cites W2335728318 @default.
• W2968706510 cites W2412320034 @default.
• W2968706510 cites W2432004435 @default.
• W2968706510 cites W2520742745 @default.
• W2968706510 cites W2528092473 @default.
• W2968706510 cites W2536626143 @default.
• W2968706510 cites W2556197365 @default.
• W2968706510 cites W2563764042 @default.
• W2968706510 cites W2576909490 @default.
• W2968706510 cites W2596585942 @default.
• W2968706510 cites W2606347107 @default.
• W2968706510 cites W2613184245 @default.
• W2968706510 cites W2616803684 @default.
• W2968706510 cites W2618839904 @default.
• W2968706510 cites W2734523407 @default.
• W2968706510 cites W273955616 @default.
• W2968706510 cites W2739748921 @default.
• W2968706510 cites W2757028014 @default.
• W2968706510 cites W2792373886 @default.
• W2968706510 cites W2795087793 @default.
• W2968706510 cites W2795722336 @default.
• W2968706510 cites W2798391154 @default.
• W2968706510 cites W2798724920 @default.
• W2968706510 cites W2820727372 @default.
• W2968706510 cites W2884971888 @default.
• W2968706510 cites W2941607568 @default.
• W2968706510 cites W2949117887 @default.
• W2968706510 cites W2949995983 @default.
• W2968706510 cites W2962835968 @default.
• W2968706510 cites W2962892300 @default.
• W2968706510 cites W2963128427 @default.
• W2968706510 cites W2963628712 @default.
• W2968706510 cites W2963684088 @default.
• W2968706510 cites W2964040467 @default.
• W2968706510 cites W2964201867 @default.
• W2968706510 cites W2967622921 @default.
• W2968706510 cites W3100866725 @default.
• W2968706510 cites W3105024549 @default.
• W2968706510 cites W3118608800 @default.
• W2968706510 cites W3138285557 @default.
• W2968706510 cites W830076066 @default.
• W2968706510 doi "https://doi.org/10.48550/arxiv.1908.03850" @default.
• W2968706510 hasPublicationYear "2019" @default.
• W2968706510 type Work @default.
• W2968706510 sameAs 2968706510 @default.
• W2968706510 citedByCount "0" @default.
• W2968706510 crossrefType "posted-content" @default.
• W2968706510 hasAuthorship W2968706510A5006832020 @default.
• W2968706510 hasAuthorship W2968706510A5028229824 @default.
• W2968706510 hasAuthorship W2968706510A5032806437 @default.
• W2968706510 hasAuthorship W2968706510A5042967567 @default.
• W2968706510 hasAuthorship W2968706510A5059454224 @default.
• W2968706510 hasAuthorship W2968706510A5080722708 @default.
• W2968706510 hasBestOaLocation W29687065101 @default.
• W2968706510 hasConcept C108583219 @default.
• W2968706510 hasConcept C119857082 @default.
• W2968706510 hasConcept C13280743 @default.
• W2968706510 hasConcept C136389625 @default.
• W2968706510 hasConcept C153180895 @default.
• W2968706510 hasConcept C154945302 @default.
• W2968706510 hasConcept C185798385 @default.

• next