ScholarGate
Asistent

Usporedite metode

Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.

Slabo nadzirana konvolucijska neuronska mreža×Fino ugađana konvolucijska neuronska mreža×
PodručjeDuboko učenjeDuboko učenje
ObiteljMachine learningMachine learning
Godina nastanka2015–20162012–2014
TvoracOquab, M. et al.; Zhou, B. et al.Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward
VrstaWeakly supervised deep learningTransfer learning technique (supervised fine-tuning)
Temeljni izvorZhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2921–2929. DOI ↗Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27. link ↗
Drugi naziviWS-CNN, weakly supervised CNN, CNN with weak labels, CNN with noisy labelsFine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network
Srodne55
SažetakA weakly supervised CNN is a convolutional neural network trained with incomplete, coarse, or noisy annotations instead of full pixel-level or bounding-box labels. Typical weak labels include image-level class tags, partial annotations, or crowd-sourced noisy labels. The model learns to classify and often to roughly localize objects using these cheaper, lower-quality supervision signals.Fine-tuning a CNN means starting from a network already trained on a large dataset — typically ImageNet — and continuing training on a smaller target dataset so the model adapts its learned visual features to a new task. This approach dramatically reduces the data and compute required to reach strong performance compared with training from scratch.
ScholarGateSkup podataka
  1. v1
  2. 2 Izvori
  3. PUBLISHED
  1. v1
  2. 2 Izvori
  3. PUBLISHED

Idi na pretraživanje Preuzmi prezentaciju

ScholarGateUsporedite metode: Weakly supervised convolutional neural network · Fine-Tuned Convolutional Neural Network. Preuzeto 2026-06-17 s https://scholargate.app/hr/compare