AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Vocabulary-free Image Classification

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

NeurIPS 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 6 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
Use CaSED retrieval and candidate scoring rather than BLIP-2 VQAVIC classification · Ten-dataset averageCluster Accuracy: 43.1 vs 38.7; +4.4%Improved
Use CaSED rather than BLIP-2 VQAVIC classification · Ten-dataset averageSemantic IoU: 17.7 vs 16.0; +1.7%Improved
Use combined visual and language candidate scoring (ablation)CaSED · Ten-dataset averageCluster Accuracy: 41.7 -> 43.1; +1.4%Improved
Use language-only candidate scoring instead of visual-only scoring (ablation)CaSED · Ten-dataset averageCluster Accuracy: 41.7 -> 42.7; +1%Improved
Generate candidates from retrieved captions rather than BLIP-2 generation (ablation)CaSED with visual scoring · Ten-dataset averageCluster Accuracy: 23.3 -> 41.7Improved
Use CC12M alone rather than the combined database (ablation)CaSED · Ten-dataset averageCluster Accuracy: 43.1 -> 44.0Improved
Use CC3M rather than the combined database (ablation)CaSED · Ten-dataset averageCluster Accuracy: 34.2 vs 43.1; +8.9% over CC3MHurt
Retrieve 10 captions rather than 1 (ablation)CaSED · Ten-dataset averageCluster Accuracy: 30.9 -> 43.1Improved
Retrieve 20 captions rather than 10 (ablation)CaSED · Ten-dataset averageSemantic Similarity: 50.4 -> 49.3Hurt
Add candidate removal operations (ablation)CaSED candidate filtering · Ten-dataset averageCluster Accuracy: 27.7 -> 34.1; +6.4%Improved
Add candidate standardization after removal (ablation)CaSED candidate filtering · Ten-dataset averageCluster Accuracy: 34.1 -> 41.3; +7.2%Improved
Add final POS and occurrence filtering (ablation)CaSED candidate filtering · Ten-dataset averageCluster Accuracy: 41.3 -> 43.1Improved

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