AI Paper Atlas

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

Teach CLIP to Develop a Number Sense for Ordinal Regression

Yao DU, Qiang Zhai, Weihang Dai, Xiaomeng Li

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Fine-grained improvements to CLIP · 18 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 ranking-based feature regularizer (FCRC) to coarse-to-fine baseline (ablation)NumCLIP baseline · MORPH IIMAE: 2.25 -> 2.15Improved
add linguistic concept mapping of numbers to coarse-to-fine baseline (ablation)NumCLIP baseline · MORPH IIMAE: 2.25 -> 2.16Improved
combine linguistic concepts with ranking regularizer (ablation)NumCLIP baseline · MORPH IIMAE: 2.25 -> 2.08Improved
use coarse-to-fine paradigm alone versus OrdinalCLIP (ablation)CLIP ordinal regression · MORPH IIMAE: 2.32 -> 2.25Improved
use squared or square-root label distance instead of absolute distance for negative weights (ablation)NumCLIP · MORPH IIMAE: 2.08 -> 2.11 / 2.12No clear effect
fine-tune CLIP prompts (CoOp) instead of zero-shotCLIP · MORPH IIMAE: 6.09 -> 2.39Improved
NumCLIP versus L2RCLIP in few-shot (1-shot)CLIP ordinal regression · MORPH II 1-shotMAE: 4.54 -> 3.61Improved
NumCLIP versus L2RCLIP at 32-shotCLIP ordinal regression · MORPH II 32-shotMAE: 2.55 -> 2.60Hurt
NumCLIP versus L2RCLIP on historical image datingCLIP ordinal regression · Historical Image Datingaccuracy (%): 67.22 -> 69.61Improved

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