ScholarGate
دستیار

مقایسهٔ روش‌ها

روش‌های انتخابی خود را کنار هم مرور کنید؛ ردیف‌های متفاوت برجسته شده‌اند.

طبقه‌بندی تصویر نیمه‌نظارت‌شده×طبقه‌بندی تصویر با تنظیم دقیق (Fine-Tuned Image Classification)×
حوزهیادگیری عمیقیادگیری عمیق
خانوادهMachine learningMachine learning
سال پیدایش2013–20202010–2014
پدیدآورLee, D.-H. (pseudo-label); Sohn et al. (FixMatch)Yosinski, J. et al.; Pan, S. J. & Yang, Q.
نوعSemi-supervised deep learningTransfer learning / fine-tuning
منبع بنیادینLee, D.-H. (2013). Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. ICML 2013 Workshop on Challenges in Representation Learning. link ↗Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems (NeurIPS), 27, 3320–3328. link ↗
نام‌های دیگرSSL image classification, semi-supervised CNN classification, pseudo-label image classification, label-efficient image classificationfine-tuning for image recognition, transfer learning image classifier, pretrained CNN fine-tuning, domain-specific image classifier
مرتبط55
خلاصهSemi-supervised image classification trains deep neural networks on a small set of labeled images together with a much larger pool of unlabeled images. Techniques such as pseudo-labeling, consistency regularization, and confidence thresholding allow the model to leverage the structure of unlabeled data, dramatically reducing the need for expensive manual annotation while approaching fully-supervised accuracy.Fine-tuned image classification adapts a large neural network pretrained on a broad image corpus (such as ImageNet) to a specific target domain by continuing training on labeled domain images. This approach achieves strong accuracy with far fewer target-domain samples than training from scratch, making it the dominant paradigm for applied computer vision tasks.
ScholarGateمجموعه‌داده
  1. v1
  2. 2 منابع
  3. PUBLISHED
  1. v1
  2. 2 منابع
  3. PUBLISHED

رفتن به جست‌وجو دریافت اسلایدها

ScholarGateمقایسهٔ روش‌ها: Semi-supervised Image Classification · Fine-Tuned Image Classification. بازیابی‌شده در 2026-06-15 از https://scholargate.app/fa/compare