Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035725370> ?p ?o ?g. }
- W3035725370 abstract "Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2) detectors tend to focus on discriminative parts rather than entire objects; (3) without ground truth, object proposals have to be redundant for high recalls, causing significant memory consumption. Addressing these challenges is difficult, as it often requires to eliminate uncertainties and trivial solutions. To target these issues we develop an instance-aware and context-focused unified framework. It employs an instance-aware self-training algorithm and a learnable Concrete DropBlock while devising a memory-efficient sequential batch back-propagation. Our proposed method achieves state-of-the-art results on COCO (12.1% AP, 24.8% AP50), VOC 2007 (54.9% AP), and VOC 2012 (52.1% AP), improving baselines by great margins. In addition, the proposed method is the first to benchmark ResNet based models and weakly supervised video object detection. Refer to our project page for code, models, and more details: https://github.com/NVlabs/wetectron." @default.
- W3035725370 created "2020-06-19" @default.
- W3035725370 creator A5012009678 @default.
- W3035725370 creator A5024951066 @default.
- W3035725370 creator A5030649976 @default.
- W3035725370 creator A5049638480 @default.
- W3035725370 creator A5054586129 @default.
- W3035725370 creator A5056503617 @default.
- W3035725370 creator A5076516617 @default.
- W3035725370 date "2020-06-01" @default.
- W3035725370 modified "2023-10-12" @default.
- W3035725370 title "Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection" @default.
- W3035725370 cites W1536680647 @default.
- W3035725370 cites W1934621328 @default.
- W3035725370 cites W1936750108 @default.
- W3035725370 cites W1991367009 @default.
- W3035725370 cites W2016016818 @default.
- W3035725370 cites W2020477327 @default.
- W3035725370 cites W2031489346 @default.
- W3035725370 cites W2088049833 @default.
- W3035725370 cites W2102605133 @default.
- W3035725370 cites W2108598243 @default.
- W3035725370 cites W2119717200 @default.
- W3035725370 cites W2194775991 @default.
- W3035725370 cites W2220111505 @default.
- W3035725370 cites W2441255125 @default.
- W3035725370 cites W2559348937 @default.
- W3035725370 cites W2560474170 @default.
- W3035725370 cites W2600144439 @default.
- W3035725370 cites W2604260814 @default.
- W3035725370 cites W2606831796 @default.
- W3035725370 cites W2607037079 @default.
- W3035725370 cites W2613833277 @default.
- W3035725370 cites W2798269247 @default.
- W3035725370 cites W2798748179 @default.
- W3035725370 cites W2954087924 @default.
- W3035725370 cites W2958020048 @default.
- W3035725370 cites W2963016543 @default.
- W3035725370 cites W2963037989 @default.
- W3035725370 cites W2963045696 @default.
- W3035725370 cites W2963150697 @default.
- W3035725370 cites W2963490895 @default.
- W3035725370 cites W2963498646 @default.
- W3035725370 cites W2963603913 @default.
- W3035725370 cites W2963697527 @default.
- W3035725370 cites W2963949812 @default.
- W3035725370 cites W2963952323 @default.
- W3035725370 cites W2964286567 @default.
- W3035725370 cites W2964328846 @default.
- W3035725370 cites W2985406498 @default.
- W3035725370 cites W2991023920 @default.
- W3035725370 cites W2991662170 @default.
- W3035725370 cites W2994041372 @default.
- W3035725370 cites W318792885 @default.
- W3035725370 cites W4300402905 @default.
- W3035725370 doi "https://doi.org/10.1109/cvpr42600.2020.01061" @default.
- W3035725370 hasPublicationYear "2020" @default.
- W3035725370 type Work @default.
- W3035725370 sameAs 3035725370 @default.
- W3035725370 citedByCount "94" @default.
- W3035725370 countsByYear W30357253702020 @default.
- W3035725370 countsByYear W30357253702021 @default.
- W3035725370 countsByYear W30357253702022 @default.
- W3035725370 countsByYear W30357253702023 @default.
- W3035725370 crossrefType "proceedings-article" @default.
- W3035725370 hasAuthorship W3035725370A5012009678 @default.
- W3035725370 hasAuthorship W3035725370A5024951066 @default.
- W3035725370 hasAuthorship W3035725370A5030649976 @default.
- W3035725370 hasAuthorship W3035725370A5049638480 @default.
- W3035725370 hasAuthorship W3035725370A5054586129 @default.
- W3035725370 hasAuthorship W3035725370A5056503617 @default.
- W3035725370 hasAuthorship W3035725370A5076516617 @default.
- W3035725370 hasBestOaLocation W30357253702 @default.
- W3035725370 hasConcept C119857082 @default.
- W3035725370 hasConcept C120665830 @default.
- W3035725370 hasConcept C121332964 @default.
- W3035725370 hasConcept C13280743 @default.
- W3035725370 hasConcept C151730666 @default.
- W3035725370 hasConcept C153180895 @default.
- W3035725370 hasConcept C154945302 @default.
- W3035725370 hasConcept C177264268 @default.
- W3035725370 hasConcept C185798385 @default.
- W3035725370 hasConcept C192209626 @default.
- W3035725370 hasConcept C199360897 @default.
- W3035725370 hasConcept C205649164 @default.
- W3035725370 hasConcept C2776151529 @default.
- W3035725370 hasConcept C2776760102 @default.
- W3035725370 hasConcept C2779343474 @default.
- W3035725370 hasConcept C2781238097 @default.
- W3035725370 hasConcept C41008148 @default.
- W3035725370 hasConcept C86803240 @default.
- W3035725370 hasConcept C97931131 @default.
- W3035725370 hasConceptScore W3035725370C119857082 @default.
- W3035725370 hasConceptScore W3035725370C120665830 @default.
- W3035725370 hasConceptScore W3035725370C121332964 @default.
- W3035725370 hasConceptScore W3035725370C13280743 @default.
- W3035725370 hasConceptScore W3035725370C151730666 @default.
- W3035725370 hasConceptScore W3035725370C153180895 @default.
- W3035725370 hasConceptScore W3035725370C154945302 @default.
- W3035725370 hasConceptScore W3035725370C177264268 @default.