手法を比較

	弱教師あり物体検出	画像分類
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2016 (deep WSOD); MIL roots circa 1997	2012 (deep CNN era); conceptual roots 1989 (LeCun)
提唱者	Bilen, H. & Vedaldi, A. (WSDDN); Multiple Instance Learning origins: Dietterich et al. (1997)	Krizhevsky, A.; Sutskever, I.; Hinton, G. E.
種類	Weakly supervised detection paradigm	Supervised classification task
原典	Bilen, H., & Vedaldi, A. (2016). Weakly supervised deep detection networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2846–2854.	Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems (NeurIPS), 25, 1097–1105.
別名	WSOD, weakly-supervised detection, image-level supervised detection, multiple instance detection	visual classification, image recognition, CNN-based classification, visual categorization
関連	5	5
概要	Weakly Supervised Object Detection (WSOD) trains object detectors using only image-level labels — indicating which object classes appear in an image — without requiring costly bounding-box annotations. Multiple Instance Learning (MIL) formulations allow the model to discover the likely location of each object class from classification signals alone, dramatically reducing annotation cost.	Image classification is the task of assigning a single semantic label to an entire image from a fixed set of categories. Modern approaches rely on deep convolutional neural networks (CNNs) or Vision Transformers (ViTs) trained end-to-end on large labeled datasets such as ImageNet, achieving superhuman accuracy on many benchmarks and underpinning applications from medical imaging to autonomous vehicles.