Сравнение методов

	Слабо контролируемое обнаружение объектов	Классификация изображений
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2016 (deep WSOD); MIL roots circa 1997	2012 (deep CNN era); conceptual roots 1989 (LeCun)
Автор метода	Bilen, H. & Vedaldi, A. (WSDDN); Multiple Instance Learning origins: Dietterich et al. (1997)	Krizhevsky, A.; Sutskever, I.; Hinton, G. E.
Тип	Weakly supervised detection paradigm	Supervised classification task
Основополагающий источник	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.
Другие названия	WSOD, weakly-supervised detection, image-level supervised detection, multiple instance detection	visual classification, image recognition, CNN-based classification, visual categorization
Связанные	5	5
Сводка	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.