השוואת שיטות

	פילוח סמנטי מוסבר	מנגנון קשב
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2019–2021	2015
הוגה השיטה	Combination: Long et al. (FCN) + Selvaraju et al. (Grad-CAM); formalized as a unified paradigm ~2019–2021	Bahdanau, D.; Luong, M.T.
סוג	Explainable deep learning pipeline	Neural attention layer (encoder-decoder)
מקור מכונן	Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 618–626.	Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR.
כינויים	XSS, interpretable semantic segmentation, explainable scene parsing, transparent pixel-wise classification	Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention
קשורות	4	5
תקציר	Explainable Semantic Segmentation (XSS) couples pixel-wise scene parsing — assigning a class label to every pixel in an image — with post-hoc or intrinsic explanation methods such as Grad-CAM, attention maps, or SHAP, so that the network's class decisions can be audited, visualized, and justified to domain experts in medical imaging, autonomous driving, and remote sensing.	The attention mechanism, introduced by Bahdanau, Cho and Bengio in 2015 and refined by Luong, Pham and Manning the same year, lets a sequence decoder dynamically learn which of the encoder's outputs to focus on at each step. Before the Transformer, it substantially improved machine-translation quality by freeing models from compressing an entire input into a single fixed vector.