AI Paper Atlas

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

OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression

Wanhua Li, Xiaoke Huang, Zheng Zhu, Yansong Tang, Xiu Li, Jie Zhou, Jiwen Lu

NeurIPS 2022 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 10 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 language prototypes with learned ordinal rank embeddings instead of a linear classification headOrdinalCLIP · MORPH IIMAE: 2.63 -> 2.32Improved
Use language prototypes with learned ordinal rank embeddings instead of CoOp promptsOrdinalCLIP · AdienceAccuracy: 60.6 ± 5.5 -> 61.2 ± 4.2Improved
Use language prototypes with learned ordinal rank embeddings instead of CoOp promptsOrdinalCLIP · Image Aesthetics overallMAE: 0.302 -> 0.280Improved
Use language prototypes with learned ordinal rank embeddings instead of CoOp promptsOrdinalCLIP · Historical Image DatingAccuracy: 51.90 ± 2.60 -> 56.44 ± 1.66Improved
Use 3 base ranks with linear interpolation rather than 2 base ranks (ablation)OrdinalCLIP · MORPH IIMAE: 2.38 -> 2.32Improved
Use linear interpolation with 3 base ranks rather than inverse-proportion interpolation with 7 base ranks (ablation)OrdinalCLIP · MORPH IIMAE: 2.35 -> 2.32Improved
Tune rank and context embeddings jointly rather than context embeddings only (ablation)OrdinalCLIP · MORPH IIMAE: 2.37 -> 2.36Improved
Initialize context with the task-specific prompt and tune both embeddings (ablation)OrdinalCLIP · MORPH IIMAE: 2.36 -> 2.32Improved
Tune rank embeddings only rather than both rank and context embeddings (ablation)OrdinalCLIP · MORPH IIMAE: 2.32 -> 2.38Hurt
Tune context embeddings only rather than both rank and context embeddings (ablation)OrdinalCLIP · MORPH IIMAE: 2.32 -> 2.37Hurt
Add ordinal rank embeddings to CoOp context-only tuning (ablation)CoOp · MORPH IIMAE: 2.44 -> 2.39Improved
Use language-guided ordinal prompts instead of CNN Baseline in one-shot trainingOrdinalCLIP · MORPH II, 1 shotMAE: 8.04 -> 4.94Improved

Later papers that compared with this method

3 later accepted papers report OrdinalCLIP as a baseline in their results tables; 3 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