Machine learning

Faster R-CNN

Faster R-CNN je dvostupanjski okvir za detekciju objekata utemeljen na dubokim konvolucijskim mrežama, koji su predstavili Shaoqing Ren, Kaiming He, Ross Girshick i Jian Sun (Microsoft Research) na konferenciji NeurIPS 2015. Zamjenjuje spor korak predlaganja regija selektivnim pretraživanjem, korišten u njegovim prethodnicima R-CNN i Fast R-CNN, naučenom mrežom za predlaganje regija (Region Proposal Network, RPN) koja dijeli konvolucijske značajke s glavom za detekciju, omogućujući prvu potpuno end-to-end podučivu, gotovo u stvarnom vremenu preciznu detekciju objekata i postavljajući dugoročni mjerilo točnosti na PASCAL VOC i MS COCO.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Advances in Neural Information Processing Systems (NeurIPS), 28, 91–99. link
  2. Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149. DOI: 10.1109/TPAMI.2016.2577031
  3. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Ch. 9: Convolutional Networks). MIT Press. ISBN: 978-0-262-03561-3

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Faster Region-based Convolutional Neural Network. ScholarGate. https://scholargate.app/hr/deep-learning/faster-r-cnn

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.

Compare side by side

Citirana u

ScholarGateFaster R-CNN (Faster Region-based Convolutional Neural Network). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/faster-r-cnn · Skup podataka: https://doi.org/10.5281/zenodo.20539026