Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092932168> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3092932168 abstract "Weakly Supervised Object Localization (WSOL) aims to learn object locations in a given image while only using image-level annotations. For highlighting the whole object regions instead of the discriminative parts, previous works often attempt to train classification model for both classification and localization tasks. However, it is hard to achieve a good tradeoff between the two tasks, if only classification labels are employed for training on a single classification model. In addition, all of recent works just perform localization based on the last convolutional layer of classification model, ignoring the localization ability of other layers. In this work, we propose an offline framework to achieve precise localization on any convolutional layer of a classification model by exploiting two kinds of gradients, called Dual-Gradients Localization (DGL) framework. DGL framework is developed based on two branches: 1) Pixel-level Class Selection, leveraging gradients of the target class to identify the correlation ratio of pixels to the target class within any convolutional feature maps, and 2) Class-aware Enhanced Maps, utilizing gradients of classification loss function to mine entire target object regions, which would not damage classification performance. Extensive experiments on public ILSVRC and CUB-200-2011 datasets show the effectiveness of the proposed DGL framework. Especially, our DGL obtains a new state-of-the-art Top-1 localization error of 43.55% on the ILSVRC benchmark." @default.
- W3092932168 created "2020-10-22" @default.
- W3092932168 creator A5005868375 @default.
- W3092932168 creator A5006854141 @default.
- W3092932168 creator A5028127027 @default.
- W3092932168 creator A5078290333 @default.
- W3092932168 creator A5080706260 @default.
- W3092932168 date "2020-10-12" @default.
- W3092932168 modified "2023-10-18" @default.
- W3092932168 title "Dual-Gradients Localization Framework for Weakly Supervised Object Localization" @default.
- W3092932168 cites W2117539524 @default.
- W3092932168 cites W2161185676 @default.
- W3092932168 cites W2183341477 @default.
- W3092932168 cites W2194775991 @default.
- W3092932168 cites W2295107390 @default.
- W3092932168 cites W2585521554 @default.
- W3092932168 cites W2600144439 @default.
- W3092932168 cites W2606831796 @default.
- W3092932168 cites W2752782242 @default.
- W3092932168 cites W2776207810 @default.
- W3092932168 cites W2788159735 @default.
- W3092932168 cites W2798376494 @default.
- W3092932168 cites W2799124825 @default.
- W3092932168 cites W2883554151 @default.
- W3092932168 cites W2950557962 @default.
- W3092932168 cites W2954345245 @default.
- W3092932168 cites W2962758679 @default.
- W3092932168 cites W2962858109 @default.
- W3092932168 cites W2963037989 @default.
- W3092932168 cites W2963045696 @default.
- W3092932168 cites W2963795442 @default.
- W3092932168 cites W2963952323 @default.
- W3092932168 cites W2964274719 @default.
- W3092932168 cites W2982093251 @default.
- W3092932168 cites W2990371274 @default.
- W3092932168 cites W2992308087 @default.
- W3092932168 cites W2994041372 @default.
- W3092932168 cites W3106250896 @default.
- W3092932168 doi "https://doi.org/10.1145/3394171.3413622" @default.
- W3092932168 hasPublicationYear "2020" @default.
- W3092932168 type Work @default.
- W3092932168 sameAs 3092932168 @default.
- W3092932168 citedByCount "5" @default.
- W3092932168 countsByYear W30929321682022 @default.
- W3092932168 crossrefType "proceedings-article" @default.
- W3092932168 hasAuthorship W3092932168A5005868375 @default.
- W3092932168 hasAuthorship W3092932168A5006854141 @default.
- W3092932168 hasAuthorship W3092932168A5028127027 @default.
- W3092932168 hasAuthorship W3092932168A5078290333 @default.
- W3092932168 hasAuthorship W3092932168A5080706260 @default.
- W3092932168 hasConcept C124952713 @default.
- W3092932168 hasConcept C142362112 @default.
- W3092932168 hasConcept C153180895 @default.
- W3092932168 hasConcept C154945302 @default.
- W3092932168 hasConcept C2780980858 @default.
- W3092932168 hasConcept C2781238097 @default.
- W3092932168 hasConcept C31972630 @default.
- W3092932168 hasConcept C41008148 @default.
- W3092932168 hasConceptScore W3092932168C124952713 @default.
- W3092932168 hasConceptScore W3092932168C142362112 @default.
- W3092932168 hasConceptScore W3092932168C153180895 @default.
- W3092932168 hasConceptScore W3092932168C154945302 @default.
- W3092932168 hasConceptScore W3092932168C2780980858 @default.
- W3092932168 hasConceptScore W3092932168C2781238097 @default.
- W3092932168 hasConceptScore W3092932168C31972630 @default.
- W3092932168 hasConceptScore W3092932168C41008148 @default.
- W3092932168 hasLocation W30929321681 @default.
- W3092932168 hasOpenAccess W3092932168 @default.
- W3092932168 hasPrimaryLocation W30929321681 @default.
- W3092932168 hasRelatedWork W1837097281 @default.
- W3092932168 hasRelatedWork W1966410754 @default.
- W3092932168 hasRelatedWork W2007544051 @default.
- W3092932168 hasRelatedWork W2016398835 @default.
- W3092932168 hasRelatedWork W2030539674 @default.
- W3092932168 hasRelatedWork W2095705906 @default.
- W3092932168 hasRelatedWork W2325242284 @default.
- W3092932168 hasRelatedWork W2363840281 @default.
- W3092932168 hasRelatedWork W2789220062 @default.
- W3092932168 hasRelatedWork W2975200075 @default.
- W3092932168 isParatext "false" @default.
- W3092932168 isRetracted "false" @default.
- W3092932168 magId "3092932168" @default.
- W3092932168 workType "article" @default.