手法を比較

	ファインチューニングされた畳み込みニューラルネットワーク	物体検出
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2012–2014	2014–2016
提唱者	Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward	Girshick, R. et al. (R-CNN); Redmon, J. et al. (YOLO)
種類	Transfer learning technique (supervised fine-tuning)	Supervised deep learning (region proposal or single-shot)
原典	Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27.	Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 580–587.
別名	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network	visual object detection, image object localization, region-based object detection, bounding-box detection
関連	5	3
概要	Fine-tuning a CNN means starting from a network already trained on a large dataset — typically ImageNet — and continuing training on a smaller target dataset so the model adapts its learned visual features to a new task. This approach dramatically reduces the data and compute required to reach strong performance compared with training from scratch.	Object detection is a computer vision task in which a deep neural network simultaneously locates and classifies every instance of one or more object categories within an image, producing a bounding box and a class label for each detected object. Modern detectors — from the R-CNN family to YOLO and DETR — achieve near-human accuracy at real-time speeds on standard benchmarks.