AI Paper Atlas

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

Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network

Shir Gur, Lior Wolf, Lior Golgher, Pablo Blinder

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 62 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
add rank loss L_rank (ablation)Ours · DeepVess datasetAP: 0.100 -> 0.909Improved
add rank loss L_rank (ablation)Ours · DeepVess datasetDICE: 0.159 -> 0.829Improved
add active contour loss L_AC (ablation)Ours · DeepVess datasetAP: 0.617 -> 0.909Improved
add active contour loss L_AC (ablation)Ours · DeepVess datasetDICE: 0.437 -> 0.829Improved
add morphological pooling layers (S instead of S-bar) (ablation)Ours · DeepVess datasetDICE: 0.707 -> 0.829Improved
add morphological pooling layers (S instead of S-bar) (ablation)Ours · DeepVess datasetAP: 0.831 -> 0.909Improved
add remaining losses (tight, rec, MV, ME) to L_AC + L_rank (ablation)Ours · DeepVess datasetDICE: 0.817 -> 0.829Improved
add L_rank to L_AC alone (ablation)Ours · DeepVess datasetDICE: 0.798 -> 0.817Improved
unsupervised fine-tuning on test-domain data (FT)Ours · DeepVess dataset -> VesselNN datasetDICE: 0.662 -> 0.715Improved
unsupervised fine-tuning on test-domain data (FT)Ours · VesselNN dataset -> DeepVess datasetDICE: 0.803 -> 0.808No clear effect
unsupervised method instead of supervised DeepVess in cross-dataset transfersegmentation · VesselNN dataset -> DeepVess datasetDICE: 0.506 -> 0.803Improved
unsupervised method instead of supervised DeepVess in within-dataset trainingsegmentation · VesselNN datasetDICE: 0.757 -> 0.776Improved

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