השוואת שיטות

	פילוח סמנטי מולטימודאלי	טרנספורמר ראייה
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2014–2016	2021
הוגה השיטה	Multiple contributors (Hazirbas et al., Long et al., and others)	Dosovitskiy, A. et al.
סוג	Pixel-level classification with multi-sensor fusion	Transformer architecture for images (self-attention over patches)
מקור מכונן	Hazirbas, C., Ma, L., Domokos, C., & Cremers, D. (2016). FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. In Proceedings of the Asian Conference on Computer Vision (ACCV). Springer.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
כינויים	multimodal scene parsing, multi-sensor semantic segmentation, RGB-D semantic segmentation, cross-modal semantic segmentation	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
קשורות	3	5
תקציר	Multimodal semantic segmentation assigns a semantic class label to every pixel in a scene by fusing information from two or more sensor modalities — most commonly RGB images paired with depth maps (RGB-D), LiDAR point clouds, thermal cameras, or text descriptions. Deep encoder-decoder networks learn to align and fuse complementary cues from each modality, producing denser and more accurate segmentation than any single-modality approach.	The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).