AI Paper Atlas

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

Segmenting Known Objects and Unseen Unknowns without Prior Knowledge

Stefano Gasperini, Alvaro Marcos-Ramiro, Michael Schmidt, Nassir Navab, Benjamin Busam, Federico Tombari

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 12 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 a dedicated prototype head (ablation)U3HS · Lost&Found (unseen)PQ: 3.64 -> 7.94Improved
add relaxed embedding association (ablation)semantic uncertainty baseline · Lost&Found (unseen)PQ: 0.49 -> 3.64Improved
add semantic uncertainty branch without other components (ablation)OSIS-style baseline · Lost&Found (unseen)PQ: 1.45 -> 0.49Hurt
add majority voting for instance class (ablation)U3HS · Cityscapes (open)PQ: 23.94 -> 39.84Improved
add reassigning of DBSCAN outliers (ablation)U3HS · Cityscapes (open)PQ: 39.84 -> 41.21Improved
add reassigning of DBSCAN outliers (ablation)U3HS · Lost&Found (unseen)PQ: 7.85 -> 7.94No clear effect
learn semantic-aware embeddings (ablation)U3HS · Lost&Found (unseen)PQ: 2.33 -> 7.85Improved
use improved DPN uncertainty instead of softmax (ablation)U3HS · Lost&Found (unseen)PQ: 0.10 -> 7.94Improved
use improved DPN instead of original DPN (ablation)U3HS · Lost&Found (unseen)PQ: 2.09 -> 7.94Improved
use uncertainty plus instance-aware embeddings instead of learning voidU3HS vs OSIS · Lost&Found (unseen)PQ: 1.45 -> 7.94Improved
switch from closed to open-set inferenceU3HS · CityscapesPQ: 46.53 -> 41.21Hurt
use U3HS instead of Panoptic-DeepLab for known classesCityscapes closed · Cityscapes (closed)PQ: 45.82 -> 46.53Improved

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