AI Paper Atlas

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

Vocabulary-Free Image Classification and Semantic Segmentation

Alessandro Conti, Enrico Fini, Massimiliano Mancini, Paolo Rota, Yiming Wang, Elisa Ricci

TPAMI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 8 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 prompt ensembling to CaSEDCaSED · Ten classification datasetsCluster Accuracy (%): 43.1 -> 44.1Improved
add prompt ensembling to WordNet baseline (ablation)CLIP + WordNet · Ten classification datasetsCluster Accuracy (%): 32.6 -> 33.3Improved
add prompt ensembling to English Words baseline (ablation)CLIP + English Words · Ten classification datasetsCluster Accuracy (%): 30.4 -> 29.6Hurt
add remove operations in candidate filtering (ablation)CaSED · Ten classification datasetsCluster Accuracy (%): 27.7 -> 34.1Mixed
add standardize operations (lowercase, singular) (ablation)CaSED · Ten classification datasetsCluster Accuracy (%): 34.1 -> 41.3Improved
add POS and occurrence filtering (ablation)CaSED · Ten classification datasetsCluster Accuracy (%): 41.3 -> 43.1Improved
retrieve 10 captions instead of 1 (ablation)CaSED · Ten classification datasetsCluster Accuracy (%): 30.9 -> 43.1Improved
retrieve 20 captions instead of 10 (ablation)CaSED · Ten classification datasetsCluster Accuracy (%): 43.1 -> 42.9No clear effect
use SigLIP ViT-L/16 backbone instead of ResNet-50 (ablation)CaSED · ImageNet (CC12M)Cluster Accuracy (%): 32.7 -> 47.8Improved
use ViT-L/14 instead of ResNet-50 (ablation)CaSED · ImageNet (CC12M)Cluster Accuracy (%): 32.7 -> 43.5Improved
use LAION-400M database instead of PMD subset (ablation)CaSED · ImageNetCluster Accuracy (%): 41.5 -> 37.7Hurt
couple CaSED candidates with SAN instead of English WordsSAN · PascalVOC-20Hard Jaccard Index (HJI): 5.8 -> 26.9Improved

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