ScholarGate
Asistent

Uporedite metode

Pregledajte izabrane metode jednu pored druge; redovi koji se razlikuju su istaknuti.

Detekcija objekata sa malo primera (FSOD)×Swin Transformer×
OblastDuboko učenjeDuboko učenje
PorodicaMachine learningMachine learning
Godina nastanka20202021
TvoracXin WangZe Liu
TipNeural network architectureNeural network architecture
Temeljni izvorWang, X., Huang, T. E., Darrell, T., Gonzalez, J. E., & Yu, F. (2020). Few-shot object detection with attention-RPN and multi-relation detector. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9050-9059). link ↗Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 10012-10022). DOI ↗
Drugi naziviFSOD, Few-shot detectionSwin, Hierarchical Vision Transformer
Srodne34
SažetakFew-Shot Object Detection (FSOD) is a meta-learning approach that enables detecting novel object classes from only a few annotated examples. Unlike standard object detection requiring hundreds of labeled instances per class, FSOD learns to quickly adapt detection models to new object categories by leveraging knowledge from base categories.The Swin Transformer is a hierarchical vision transformer introduced by Liu et al. in 2021 that uses shifted window attention to achieve computational efficiency while maintaining strong performance on computer vision tasks. Unlike the original Vision Transformer which applies global self-attention, Swin uses local window-based attention with periodic shifting to balance expressiveness and efficiency.
ScholarGateSkup podataka
  1. v1
  2. 1 Izvori
  3. PUBLISHED
  1. v1
  2. 1 Izvori
  3. PUBLISHED

Idi na pretragu Preuzmi slajdove

ScholarGateUporedite metode: Few-Shot Object Detection · Swin Transformer. Preuzeto 2026-06-18 sa https://scholargate.app/sr/compare