AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss

Rakshith Sharma Srinivasa, Jaejin Cho, Chouchang Yang, Yashas Malur Saidutta, Ching-Hua Lee, Yilin Shen, Hongxia Jin

NeurIPS 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-tuning strategies for few-shot · 5 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
CWCL instead of LiT contrastive loss (12-layer transformer text)ViT-L/16 image-text model · ImageNet zero-shotaccuracy: 66.84 -> 74.41Improved
CWCL instead of LiT (12-layer transformer text)ViT-L/16 image-text model · ImageNet-A zero-shotaccuracy: 37.31 -> 45.58Improved
CWCL instead of LiT (12-layer transformer text)ViT-L/16 image-text model · ObjectNet zero-shotaccuracy: 45.08 -> 50.5Improved
CWCL instead of LiT (BERT-large text)ViT-L/16 + BERT-large · ImageNet zero-shotaccuracy: 71.2 -> 76.48Improved
CWCL instead of LiT (BERT-large text)ViT-L/16 + BERT-large · ImageNet-A zero-shotaccuracy: 40.28 -> 47.27Improved
CWCL instead of LiT for retrievalViT-L/16 + BERT-large · MS-COCO I->T R@1recall: 34.58 -> 40.36Improved
CWCL instead of LiT for retrievalViT-L/16 + BERT-large · MS-COCO T->I R@10recall: 65.87 -> 66.06No clear effect
CWCL instead of CL for retrievalimage-text model · MS-COCO I->T R@1recall: 30.42 -> 35.10Improved
CWCL instead of CL for speech-to-intentWhisper + RoBERTa+S · SLURP zero-shottop-1 accuracy: 40.35 -> 63.80Improved
CWCL instead of CL for speech-to-intentWhisper + BART+Y · STOP zero-shottop-1 accuracy: 55.67 -> 80.99Improved
CWCL instead of CL for keyword spottingWhisper + BART+Y · GSCV2 zero-shottop-1 accuracy: 56.33 -> 88.81Improved
Pre-trained Whisper speech encoder instead of random initialization (ablation)CWCL speech-text · SLURPtop-1 accuracy: 26.17 -> 53.12Improved

Later papers that compared with this method

1 later accepted paper reports CWCL as a baseline in their results tables; 1 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