Machine learningDeep learning / NLP / CV

Samonadzorovano otkrivanje objekata

Samonadzorovano otkrivanje objekata koristi neoznačene podatke slike za pred-obuku vizuelnog „korena“ (backbone) kroz pretekst zadatke kao što su kontrastno učenje ili modeliranje maskiranih slika, a zatim usavršava „koren“ sa glavom za detekciju na manjoj označenoj bazi podataka. Ovaj pristup dramatično smanjuje oslanjanje na skupe anotacije bounding box-ova, istovremeno dostižući ili približavajući se performansama potpuno nadziranog otkrivanja.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

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

Izvori

  1. He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum Contrast for Unsupervised Visual Representation Learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9729–9738. DOI: 10.1109/CVPR42600.2020.00975
  2. Caron, M., Touvron, H., Misra, I., Jégou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging Properties in Self-Supervised Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9650–9660. DOI: 10.1109/ICCV48922.2021.00951

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Self-supervised Pre-training for Object Detection. ScholarGate. https://scholargate.app/sr/deep-learning/self-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.

Compare side by side
ScholarGateSelf-supervised Object Detection (Self-supervised Pre-training for Object Detection). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/self-supervised-object-detection · Skup podataka: https://doi.org/10.5281/zenodo.20539026