So sánh phương pháp

	Mạng nơ-ron tích chập giám sát yếu	Phân đoạn ngữ nghĩa
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2015–2016	2015
Người khởi xướng	Oquab, M. et al.; Zhou, B. et al.	Long, J., Shelhamer, E., & Darrell, T.
Loại	Weakly supervised deep learning	Dense prediction / pixel-wise classification
Công trình gốc	Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2921–2929.	Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440.
Tên gọi khác	WS-CNN, weakly supervised CNN, CNN with weak labels, CNN with noisy labels	pixel-wise classification, scene parsing, dense labeling, semantic scene segmentation
Liên quan	5	5
Tóm tắt	A weakly supervised CNN is a convolutional neural network trained with incomplete, coarse, or noisy annotations instead of full pixel-level or bounding-box labels. Typical weak labels include image-level class tags, partial annotations, or crowd-sourced noisy labels. The model learns to classify and often to roughly localize objects using these cheaper, lower-quality supervision signals.	Semantic segmentation assigns a class label to every pixel in an image, producing a dense, category-annotated map of the scene. Unlike object detection, which draws bounding boxes, it delineates the exact spatial extent of each class, making it indispensable in medical imaging, autonomous driving, satellite analysis, and any task where precise region boundaries matter.