AI Paper Atlas

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

OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection

Changsheng Lu, Zheyuan Liu, Piotr Koniusz

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 7 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 auxiliary interpolated keypoints to visual training (ablation)OpenKD · Animal Pose 1-shot novelPCK@0.1: 21.36 -> 47.54Improved
add LLM-interpolated auxiliary texts to text training (ablation)OpenKD · Animal Pose 0-shot novelPCK@0.1: 25.60 -> 63.14Improved
use chain-of-thought prompting for LLM text interpolation (ablation)OpenKD · AwA 0-shot novelPCK@0.1: 73.80 -> 78.30Improved
select interpolated text by visual-text correlation instead of false text control (ablation)OpenKD · AwA 0-shot novelPCK@0.1: 78.30 -> 62.12Hurt
add false text control sampling (FTC) rather than correlation selection (ablation)OpenKD · AwA 0-shot novelPCK@0.1: 62.12 -> 78.64Improved
repeat LLM reasoning R=3 instead of R=1 (ablation)OpenKD · AwA 0-shot novelPCK@0.1: 67.34 -> 78.64Improved
increase R from 3 to 10 (ablation)OpenKD · AwA 0-shot novelPCK@0.1: 78.64 -> 76.61No clear effect
add intra-text contrastive loss L_tt (ablation)OpenKD · AwA 0-shot novelPCK@0.1: 76.71 -> 78.28Improved
add visual-text alignment L_vt without stop-gradient (ablation)OpenKD · AwA 0-shot novelPCK@0.1: 78.28 -> 77.10Hurt
add stop gradient on text features in L_vt (ablation)OpenKD · AwA 0-shot novelPCK@0.1: 77.10 -> 78.64Improved
add visual-visual contrastive loss L_vv (ablation)OpenKD · AwAPCK@0.1: 78.64 -> 78.60No clear effect
add LLM parsing of diverse text prompts (ablation)OpenKD · Animal Pose 0-shot novel, diverse textPCK@0.1: 13.89 -> 61.45Improved

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