AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs

Tiep Le, Vasudev Lal, Phillip Howard

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling

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
Augment real MS-COCO training data with COCO-Counterfactuals at a 60% shareCLIP · Flickr30k 1K testimage-text retrieval mean: 89.06_{0.1} -> 89.53_{0.2}Improved
Augment real MS-COCO training data with COCO-Counterfactuals at a 50% shareCLIP · Flickr30k 1K testimage-text retrieval mean: 89.06_{0.1} -> 89.05_{0.1}No clear effect
Increase the counterfactual share from 50% to 60% (ablation)CLIP trained on MS-COCO and COCO-Counterfactuals · Flickr30k 1K testimage-text retrieval mean: 89.05_{0.1} -> 89.53_{0.2}Improved
Increase the counterfactual share from 60% to 67% (ablation)CLIP trained on MS-COCO and COCO-Counterfactuals · Flickr30k 1K testimage-text retrieval mean: 89.53_{0.2} -> 89.41_{0.1}Hurt
Augment real MS-COCO training data with COCO-Counterfactuals at a 50% shareCLIP · zero-shot image recognition across six datasetsmean accuracy: 78.85_{0.2} -> 79.46_{0.2}Improved
Increase the counterfactual share from 50% to 60% (ablation)CLIP trained on MS-COCO and COCO-Counterfactuals · zero-shot image recognition across six datasetsmean accuracy: 79.46_{0.2} -> 79.20_{0.2}Hurt
Train on COCO-Counterfactuals rather than an equivalent amount of real MS-COCO dataCLIP · withheld COCO-Counterfactuals testimage-text retrieval mean: 77.03 -> 83.09Improved
Remove human-annotator-incorrect synthetic pairs from training (ablation)CLIP trained with MS-COCO and COCO-Counterfactuals · Flickr30k testimage-text retrieval meanNo clear effect
Evaluate on minimally edited COCO-Counterfactuals instead of MS-COCOBridgeTower · zero-shot image-text retrievaltext retrieval R@1: -51%Hurt
Evaluate on minimally edited COCO-Counterfactuals instead of MS-COCOFlava · zero-shot image-text retrievaltext retrieval R@1: -57%Hurt
Evaluate on COCO-Counterfactuals rather than MS-COCOCLIP · zero-shot image-text retrievaltext retrieval R@1: -21%Hurt
Evaluate on COCO-Counterfactuals rather than MS-COCOCLIP · zero-shot image-text retrievalimage retrieval R@1: +5%Improved

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