Uchanganuzi wa Objekti kwa Njia ya Kudokezwa kwa Udhaifu (WSOD)
Uchanganuzi wa Objekti kwa Njia ya Kudokezwa kwa Udhaifu (WSOD) hufunza vipambanuzi vya objekti kwa kutumia tu lebo za kiwango cha picha — zikionyesha ni madarasa gani ya objekti yanayoonekana kwenye picha — bila kuhitaji maelezo ya gharama kubwa ya maboksi ya mipaka. Miundo ya Kujifunza kwa Mifano Nyingi (MIL) huruhusu modeli kugundua mahali panapowezekana pa kila darasa la objekti kutoka kwa mawimbi ya uainishaji pekee, na hivyo kupunguza kwa kiasi kikubwa gharama ya maelezo.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
Vyanzo
- Bilen, H., & Vedaldi, A. (2016). Weakly supervised deep detection networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2846–2854. DOI: 10.1109/CVPR.2016.311 ↗
- Tang, P., Wang, X., Bai, X., & Liu, W. (2017). Multiple instance detection network with online instance classifier refinement. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2843–2851. DOI: 10.1109/cvpr.2017.326 ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 3). Weakly Supervised Object Detection (WSOD). ScholarGate. https://scholargate.app/sw/deep-learning/weakly-supervised-object-detection
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- Uainishaji wa PichaUjifunzaji wa Kina↔ compare
- Uainishaji wa MatukioUjifunzaji wa Kina↔ compare
- Utambuzi wa KituUjifunzaji wa Kina↔ compare
- Uchanganuzi Semi-Nusu-Jitoleaji wa VituUjifunzaji wa Kina↔ compare
- Transformer wa MaonoUjifunzaji wa Kina↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →