Tag: #분할
Kubernetes, DevOps and MLOps, written from things we ran and measured ourselves · 2 posts
Segment Anything (SAM): Prompt Segmentation, Data Engine, and One-Time Encoder with Multi-Decoder
We examine SAM (2023), which does not pre-define "what to paint" during training, but instead takes human clicks or bounding boxes as queries to segment objects on the spot. We summarize its paper metrics: a design where
2026-10-17 · 10 min read #비전 모델#SAM#Segment Anything#분할#프롬프트U-Net and HRNet: Resolution-Preserving Architectures and Heatmap Output
Classification models shrink images to figure out "what" is in them, but tasks like ball tracking, pose estimation, and segmentation require knowing "exactly where." We examine the design rationale of U-Net (2015), which
2026-10-17 · 12 min read #비전 모델#U-Net#HRNet#히트맵#분할