ScholarGate
Msaidizi

Linganisha mbinu

Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.

Mfumo wa Kutenganisha Kila Kitu×Autoenkoda Zilizofunikwa×
NyanjaUjifunzaji wa KinaUjifunzaji wa Kina
FamiliaMachine learningMachine learning
Mwaka wa asili20232021
MwanzilishiAlexander KirillovKaiming He
AinaNeural network architectureNeural network architecture
Chanzo asiliaKirillov, A., Mintun, E., Darrell, T., & Girshick, R. (2023). Segment Anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4015-4026). DOI ↗He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009). DOI ↗
Majina mbadalaSAM, Segment AnythingMAE, Vision MAE
Zinazohusiana44
MuhtasariSegment Anything Model (SAM) is a foundation model introduced by Kirillov et al. in 2023 that can segment any object in an image given various forms of prompts. SAM is trained on a massive dataset of diverse images and learns to segment objects based on minimal user input such as points, boxes, or text descriptions.Masked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.
ScholarGateSeti ya data
  1. v1
  2. 1 Vyanzo
  3. PUBLISHED
  1. v1
  2. 1 Vyanzo
  3. PUBLISHED

Nenda kwenye utafutaji Pakua slaidi

ScholarGateLinganisha mbinu: Segment Anything Model · Masked Autoencoders. Imepatikana 2026-06-18 kutoka https://scholargate.app/sw/compare