Compara mètodes

	Segmentació semàntica multimodal	Segmentació semàntica	Vision Transformer
Camp	Aprenentatge profund	Aprenentatge profund	Aprenentatge profund
Família	Machine learning	Machine learning	Machine learning
Any d'origen	2014–2016	2015	2021
Autor original	Multiple contributors (Hazirbas et al., Long et al., and others)	Long, J., Shelhamer, E., & Darrell, T.	Dosovitskiy, A. et al.
Tipus	Pixel-level classification with multi-sensor fusion	Dense prediction / pixel-wise classification	Transformer architecture for images (self-attention over patches)
Font seminal	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.	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.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Àlies	multimodal scene parsing, multi-sensor semantic segmentation, RGB-D semantic segmentation, cross-modal semantic segmentation	pixel-wise classification, scene parsing, dense labeling, semantic scene segmentation	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Relacionats	3	5	5
Resum	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.	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.	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).