AI Paper Atlas

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

ElixirNet: Relation-Aware Network Architecture Adaptation for Medical Lesion Detection

Chenhan Jiang, Shaoju Wang, Xiaodan Liang, Hang Xu, Nong Xiao

AAAI 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Cross-domain translation and pose · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 ElixirNet with FPN instead of FPNFPN · DeepLesion test, IoU, 3 FPs/imagesensitivity (%): 81.51 -> 86.63Improved
Use ElixirNet with FPN instead of FPNFPN · DeepLesion testmAP (%): 31.5 -> 35.2Improved
Use ElixirNet with Deformv2 instead of Deformv2Deformv2 · DeepLesion test, IoU, 3 FPs/imagesensitivity (%): 84.47 -> 86.92Improved
Use ElixirNet with Deformv2 instead of Deformv2Deformv2 · DeepLesion testmAP (%): 34.3 -> 36.3Improved
Use ElixirNet with Deformv2 instead of Deformv2Deformv2 · Kits19 testmAP (%): 32.9 -> 33.6Improved
Add RTM to ElixirNet without RTM (ablation)ElixirNet multi-type detector · DeepLesion multi-type test, bonesensitivity (%): 56.52 -> 57.38Improved
Add RTM to ElixirNet without RTM (ablation)ElixirNet multi-type detector · DeepLesion multi-type test, abdomensensitivity (%): 84.14 -> 85.41Improved
Add RTM to ElixirNet without RTM (ablation)ElixirNet multi-type detector · DeepLesion multi-type test, mediastinumsensitivity (%): 83.41 -> 84.62Improved
Add RTM to ElixirNet without RTM (ablation)ElixirNet multi-type detector · DeepLesion multi-type test, kidneysensitivity (%): 60.70 -> 65.51Improved
Add RTM to ElixirNet without RTM (ablation)ElixirNet multi-type detector · DeepLesion multi-type test, pelvissensitivity (%): 80.64 -> 83.07Improved
Use the proposed medical-oriented ALB search space instead of the classification-NAS search space (ablation)ElixirNet · DeepLesion test, IoU, 3 FPs/imagesensitivity (%): 81.06 -> 83.88Improved
Use the proposed medical-oriented ALB search space instead of the classification-NAS search space (ablation)ElixirNet · DeepLesion testmAP (%): 32.1 -> 34.1Improved

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