Kujifunza kwa Kuhamisha kwa Uainishaji wa Picha
Kujifunza kwa Kuhamisha kwa Uainishaji wa Picha hutumia upya uti wa mgongo wa mtandao mkuu wa neva — kwa kawaida CNN au Vision Transformer — uliopatiwa mafunzo awali kwenye seti kubwa ya data kama vile ImageNet, na kuubadilisha ili kuainisha picha katika kikoa kipya cha lengo. Kwa kurithi sifa za jumla za kuona kutoka kwa kazi chanzo, mbinu hufikia usahihi wa juu kwa picha chache sana zilizo na lebo kuliko mafunzo kuanzia mwanzo.
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
- Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI: 10.1109/TKDE.2009.191 ↗
- Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25. link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 3). Transfer Learning with Pretrained Deep Neural Networks for Image Classification. ScholarGate. https://scholargate.app/sw/deep-learning/transfer-learning-with-image-classification
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.
- Convolutional Neural Network Iliyoendeshwa kwa KinaUjifunzaji wa Kina↔ compare
- Vision Transformer IliyobadilishwaUjifunzaji wa Kina↔ compare
- Uainishaji wa PichaUjifunzaji wa Kina↔ compare
- Kujifunza kwa Uhamishaji na Utambuzi wa VituUjifunzaji wa Kina↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →