AI Paper Atlas

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

CLAMP: Prompt-Based Contrastive Learning for Connecting Language and Animal Pose

Xu Zhang, Wen Wang, Zhe Chen, Yufei Xu, Jing Zhang, Dacheng Tao

CVPR 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 31 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 CLIP rather than ImageNet pre-trainingSimpleBaseline with ResNet-50 · AP-10K supervisedAP: 70.2 -> 70.9Improved
Use CLAMP instead of the CLIP-pretrained SimpleBaselineResNet-50 animal pose estimation · AP-10K supervisedAP: 70.9 -> 72.9Improved
Use CLAMP instead of the CLIP-pretrained SimpleBaselineViT-Base animal pose estimation · AP-10K supervisedAP: 72.6 -> 74.3Improved
Use CLIP rather than ImageNet pre-trainingSimpleBaseline with ResNet-50 · Animal-Pose supervisedAP: 68.7 -> 70.8Improved
Use CLAMP instead of the CLIP-pretrained SimpleBaselineResNet-50 animal pose estimation · Animal-Pose supervisedAP: 70.8 -> 72.5Improved
Use CLAMP instead of the CLIP-pretrained SimpleBaselineViT-Base animal pose estimation · Animal-Pose supervisedAP: 72.3 -> 74.3Improved
Use CLAMP instead of SimpleBaselineResNet-50 animal pose estimation · AP-10K, Bovidae train → Canidae testAP: 41.3 -> 46.9Improved
Use CLAMP instead of SimpleBaselineResNet-50 animal pose estimation · AP-10K, Canidae train → Felidae testAP: 39.6 -> 48.4Improved
Add spatial-level contrastive loss (ablation)CLAMP with CLIP-pretrained ResNet-50 · AP-10K supervisedAP: 70.9 -> 72.1Improved
Add feature-level contrastive loss (ablation)CLAMP with spatial-level loss · AP-10K supervisedAP: 72.1 -> 72.6Improved
Add prompt encoder (ablation)CLAMP with spatial- and feature-level losses · AP-10K supervisedAP: 72.6 -> 72.9Improved
Replace prompt embedding with a trainable matrix (ablation)CLAMP with ViT-Base · AP-10K supervisedAP: 74.3 -> 72.8Hurt

Later papers that compared with this method

3 later accepted papers report CLAMP 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