AI Paper Atlas

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

Dual Contrastive Learning with Anatomical Auxiliary Supervision for Few-Shot Medical Image Segmentation

Huisi Wu, Fangyan Xiao, Chongxin Liang

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation

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
add skip connections to sSENet (ablation)sSENet · CHAOS-T2mean Dice (%): 47.45 -> 49.08Improved
add DCL module (ablation)Baseline with skip connections · CHAOS-T2mean Dice (%): 49.08 -> 67.21Improved
add CIP module (ablation)Baseline with skip connections · CHAOS-T2mean Dice (%): 49.08 -> 62.07Improved
add CIP on top of DCL (ablation)Baseline+DCL · CHAOS-T2mean Dice (%): 67.21 -> 76.36Improved
add DCL on top of CIP (ablation)Baseline+CIP · CHAOS-T2mean Dice (%): 62.07 -> 76.36Improved
use Felzenszwalb instead of SLIC superpixels (ablation)AAS-DCL · CHAOS-T2mean Dice (%): 61.35 -> 76.36Improved
use Felzenszwalb instead of SEEDS superpixels (ablation)AAS-DCL · CHAOS-T2mean Dice (%): 67.07 -> 76.36Improved
use 5 CIP iterations instead of 3 (ablation)AAS-DCL · CHAOS-T2mean Dice (%): 72.58 -> 76.36Improved
use 7 CIP iterations instead of 5 (ablation)AAS-DCL · CHAOS-T2mean Dice (%): 76.36 -> 76.12No clear effect
use 3 non-target slices instead of 1 (ablation)AAS-DCL · CHAOS-T2mean Dice (%): 70.34 -> 76.36Improved
use 5 non-target slices instead of 3 (ablation)AAS-DCL · CHAOS-T2mean Dice (%): 76.36 -> 74.80Hurt
AAS-DCL vs RP-NetRP-Net · CHAOS-T2mean Dice (%): 75.81 -> 76.36Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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