Matches in SemOpenAlex for { <https://semopenalex.org/work/W3091460427> ?p ?o ?g. }
- W3091460427 abstract "Weakly Supervised Object Localization (WSOL) has increasingly attracted interests for only using image-level supervision instead of location annotations. Some common challenges for existing methods are that they cover only the most discriminative part of the object. And a substantial amount of noise in training causes ambiguities for learning in a robust manner. In this paper, we propose to address these drawbacks by Self-Paced Pyramid Adversarial Learning(SPAL). Specifically, for suppressing noise, we use self-paced learning (SPL) to training data from simple to complex and from coarse to fine. And our network divides two subnetworks: 1) coarse pyramid network(CPN), 2) fine pyramid network (FPN). In CPN, we aim to utilize pyramid adversarial erase mechanism to process the feature maps of different scale. Consequently, CPN can cover the entire object to generate initial object proposals. Then CPN builds the relevance score as pseudo labels of proposals. In FPN, object proposals and pseudo labels can be trained to locate precise object boundaries. Finally, We also propose adversarial loss function to fit our network. Detailed experimental results on the PASCAL VOC dataset demonstrate that SPAL performs promising against the state-of-the-art methods." @default.
- W3091460427 created "2020-10-08" @default.
- W3091460427 creator A5002671318 @default.
- W3091460427 creator A5024265320 @default.
- W3091460427 creator A5063326178 @default.
- W3091460427 creator A5064225220 @default.
- W3091460427 creator A5071320926 @default.
- W3091460427 date "2020-07-01" @default.
- W3091460427 modified "2023-09-27" @default.
- W3091460427 title "Weakly Supervised Object Localization Using Self-Paced Pyramid Adversarial Learning" @default.
- W3091460427 cites W1934621328 @default.
- W3091460427 cites W1994488211 @default.
- W3091460427 cites W1995137594 @default.
- W3091460427 cites W2037227137 @default.
- W3091460427 cites W2045724293 @default.
- W3091460427 cites W2088049833 @default.
- W3091460427 cites W2117539524 @default.
- W3091460427 cites W2124379907 @default.
- W3091460427 cites W2132984949 @default.
- W3091460427 cites W2133324800 @default.
- W3091460427 cites W2156689847 @default.
- W3091460427 cites W2194775991 @default.
- W3091460427 cites W2221436333 @default.
- W3091460427 cites W2256388387 @default.
- W3091460427 cites W2295107390 @default.
- W3091460427 cites W2296073425 @default.
- W3091460427 cites W2494236530 @default.
- W3091460427 cites W2528287124 @default.
- W3091460427 cites W2559348937 @default.
- W3091460427 cites W2565639579 @default.
- W3091460427 cites W2566871317 @default.
- W3091460427 cites W2600144439 @default.
- W3091460427 cites W2604260814 @default.
- W3091460427 cites W2613718673 @default.
- W3091460427 cites W2798748179 @default.
- W3091460427 cites W2806231060 @default.
- W3091460427 cites W2884195989 @default.
- W3091460427 cites W2950557962 @default.
- W3091460427 cites W2952072685 @default.
- W3091460427 cites W2963037989 @default.
- W3091460427 cites W2963045696 @default.
- W3091460427 cites W2963254348 @default.
- W3091460427 cites W2963603913 @default.
- W3091460427 cites W2963670239 @default.
- W3091460427 cites W2963952323 @default.
- W3091460427 cites W2964274719 @default.
- W3091460427 cites W2970732258 @default.
- W3091460427 cites W2994041372 @default.
- W3091460427 cites W3012573144 @default.
- W3091460427 cites W3106250896 @default.
- W3091460427 cites W318792885 @default.
- W3091460427 cites W7746136 @default.
- W3091460427 doi "https://doi.org/10.1109/ijcnn48605.2020.9207099" @default.
- W3091460427 hasPublicationYear "2020" @default.
- W3091460427 type Work @default.
- W3091460427 sameAs 3091460427 @default.
- W3091460427 citedByCount "0" @default.
- W3091460427 crossrefType "proceedings-article" @default.
- W3091460427 hasAuthorship W3091460427A5002671318 @default.
- W3091460427 hasAuthorship W3091460427A5024265320 @default.
- W3091460427 hasAuthorship W3091460427A5063326178 @default.
- W3091460427 hasAuthorship W3091460427A5064225220 @default.
- W3091460427 hasAuthorship W3091460427A5071320926 @default.
- W3091460427 hasConcept C119857082 @default.
- W3091460427 hasConcept C138885662 @default.
- W3091460427 hasConcept C142575187 @default.
- W3091460427 hasConcept C153180895 @default.
- W3091460427 hasConcept C154945302 @default.
- W3091460427 hasConcept C199360897 @default.
- W3091460427 hasConcept C2524010 @default.
- W3091460427 hasConcept C2776151529 @default.
- W3091460427 hasConcept C2776401178 @default.
- W3091460427 hasConcept C2781238097 @default.
- W3091460427 hasConcept C31972630 @default.
- W3091460427 hasConcept C33923547 @default.
- W3091460427 hasConcept C37736160 @default.
- W3091460427 hasConcept C41008148 @default.
- W3091460427 hasConcept C41895202 @default.
- W3091460427 hasConcept C59404180 @default.
- W3091460427 hasConcept C75608658 @default.
- W3091460427 hasConcept C97931131 @default.
- W3091460427 hasConceptScore W3091460427C119857082 @default.
- W3091460427 hasConceptScore W3091460427C138885662 @default.
- W3091460427 hasConceptScore W3091460427C142575187 @default.
- W3091460427 hasConceptScore W3091460427C153180895 @default.
- W3091460427 hasConceptScore W3091460427C154945302 @default.
- W3091460427 hasConceptScore W3091460427C199360897 @default.
- W3091460427 hasConceptScore W3091460427C2524010 @default.
- W3091460427 hasConceptScore W3091460427C2776151529 @default.
- W3091460427 hasConceptScore W3091460427C2776401178 @default.
- W3091460427 hasConceptScore W3091460427C2781238097 @default.
- W3091460427 hasConceptScore W3091460427C31972630 @default.
- W3091460427 hasConceptScore W3091460427C33923547 @default.
- W3091460427 hasConceptScore W3091460427C37736160 @default.
- W3091460427 hasConceptScore W3091460427C41008148 @default.
- W3091460427 hasConceptScore W3091460427C41895202 @default.
- W3091460427 hasConceptScore W3091460427C59404180 @default.
- W3091460427 hasConceptScore W3091460427C75608658 @default.
- W3091460427 hasConceptScore W3091460427C97931131 @default.
- W3091460427 hasLocation W30914604271 @default.