AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Alternative Baselines for Low-Shot 3D Medical Image Segmentation—An Atlas Perspective

AAAI 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 3 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the Siamese correspondence baseline instead of LT-NetCANDI 1-shot segmentation · CANDIDice (%) mean: 82.3 (2.5) -> 83.0 (1.8)Helped
Use five atlases with Siamese-Baseline instead of oneSiamese-Baseline · CANDIDice (%) mean: 83.0 (1.8) -> 86.2 (2.1)Helped
Use IDA-Baseline instead of LT-NetMulti-organ 1-shot segmentation · Multi-organDice (%) mean: 58.05 -> 61.28Helped
Use five atlases instead of oneIDA-Baseline · Multi-organDice (%) mean: 61.28 -> 68.61Helped
Add backward correspondence and forward-backward cycle consistency (ablation)Siamese-Baseline · Multi-organ 5-shotDice (%) mean: 63.64 -> 65.78Helped
Add individual-difference modeling to the cycle-consistency model (ablation)Siamese-Baseline · Multi-organ 5-shotDice (%) mean: 65.78 -> 68.61Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy