ScholarGate
Pembantu

Bandingkan kaedah

Semak kaedah pilihan anda secara bersebelahan; baris yang berbeza akan diserlahkan.

Semantic Segmentation×Transformer Visi×
BidangPembelajaran MendalamPembelajaran Mendalam
KeluargaMachine learningMachine learning
Tahun asal20152021
PengasasLong, J., Shelhamer, E., & Darrell, T.Dosovitskiy, A. et al.
JenisDense prediction / pixel-wise classificationTransformer architecture for images (self-attention over patches)
Sumber perintisLong, 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. DOI ↗Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗
Aliaspixel-wise classification, scene parsing, dense labeling, semantic scene segmentationGörsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Berkaitan55
RingkasanSemantic 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).
ScholarGateSet data
  1. v1
  2. 2 Sumber
  3. PUBLISHED
  1. v1
  2. 2 Sumber
  3. PUBLISHED

Pergi ke carian Muat turun slaid

ScholarGateBandingkan kaedah: Semantic Segmentation · Vision Transformer. Dicapai 2026-06-17 daripada https://scholargate.app/ms/compare