AI Paper Atlas

Research map / Detection and segmentation / CNN features

Mask2Anomaly: Mask Transformer for Universal Open-Set Segmentation

Shyam Nandan Rai, Fabio Cermelli, Barbara Caputo B, Carlo Masone

TPAMI 2024 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 23 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 global mask attention, contrastive learning and refinement mask to Mask2Former (ablation)Mask2Former · FS L&F valAuPRC: 10.60 -> 69.41Improved
add contrastive learning loss (to GMA + RM) (ablation)Mask2Anomaly · FS L&F valAuPRC: 35.05 -> 69.41Improved
add refinement mask (ablation)Mask2Anomaly · FS L&F valFPR95: 24.07 -> 9.46Improved
add refinement mask (ablation)Mask2Anomaly · FS L&F valAuPRC: 68.95 -> 69.41Improved
replace masked attention with global mask attention (ablation)Mask2Former · FS L&F valAuPRC: 10.60 -> 32.35Improved
replace masked attention with global mask attention (ablation)Mask2Former · FS L&F valmIoU: 77.42 -> 80.45Improved
replace masked attention with global mask attention (ablation)Mask2Former · ADE20KmIoU: 43.20 -> 43.80Improved
replace masked attention with global mask attention (ablation)Mask2Former · VistasmIoU: 38.17 -> 38.92Improved
apply refinement loss on stuff excluding road instead of things excluding road (ablation)Mask2Anomaly · FS L&F valFPR95: 39.11 -> 9.46Improved
contrastive margin 0.75 versus 0.5 (ablation)Mask2Anomaly · FS L&F valAuPRC: 62.07 -> 69.41Improved
batch outlier probability 0.2 versus 0.1 (ablation)Mask2Anomaly · FS L&F valAuPRC: 63.01 -> 69.41Improved
add mining of unknown instances (ablation)Mask2Anomaly · COCO open-set panopticPQ unknown: 9.1 -> 14.6Improved

Later papers that compared with this method

2 later accepted papers report Mask2Anomaly as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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