AI Paper Atlas

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

NLIP: Noise-Robust Language-Image Pre-training

Runhui Huang, Yanxin Long, Jianhua Han, Hang Xu, Xiwen Liang, Chunjing Xu, Xiaodan Liang

AAAI 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Self-distillation for vision-language pretraining · 24 citations (OpenAlex)

This paper tried a common change: Add positional encoding

Add positional embeddings to the 75%-masked visual encoder · ImageNet zero-shot classification · top-1 accuracy (%): 26.5 -> 27.0 Improved

What 646 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 noise-robust pre-training with noise harmonization and noise completionNLIP on YFCC26M · YFCC26M zero-shot image classification, 12-dataset average, ViT-B/16top-1 accuracy (%): 37.3 -> 45.9Improved
Use noise-robust pre-training with noise harmonization and noise completionNLIP on YFCC26M · Flickr30K zero-shot image-to-text retrievalR@1: 53.9 -> 82.6Improved
Use noise-robust pre-training with noise harmonization and noise completionNLIP on YFCC26M · MSCOCO image captioningCIDEr: 133.3 -> 135.2Improved
Add noise completion (ablation)NLIP · Flickr30K image-to-text retrievalR@1: 72.2 -> 82.6Improved
Add noise completion (ablation)NLIP · MSCOCO image captioningCIDEr: 132.4 -> 134.0Improved
Add noise harmonization (ablation)NLIP · Flickr30K text-to-image retrievalR@1: 47.1 -> 61.2Improved
Add noise harmonization (ablation)NLIP · ImageNet zero-shot classificationtop-1 accuracy (%): 46.7 -> 47.4Improved
Condition noise completion on visual concepts (ablation)NLIP · ImageNet zero-shot classificationtop-1 accuracy (%): 46.7 -> 47.4Improved
Condition noise completion on visual concepts (ablation)NLIP · Flickr30K text-to-image retrievalR@1: 60.1 -> 61.2Improved
Use YFCC visual concepts rather than no visual concepts (ablation)YFCC26M-CLIP · ImageNet zero-shot classificationtop-1 accuracy (%): 37.3 -> 42.7Improved
Use ensemble visual concepts rather than no visual concepts (ablation)YFCC26M-CLIP · ImageNet zero-shot classificationtop-1 accuracy (%): 39.2 -> 42.5Improved
Use pre-trained BART as the text encoder (ablation)CLIP architecture trained on YFCC26M · ImageNet zero-shot classificationtop-1 accuracy (%): 30.1 -> 32.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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