Text-Only Training for Image Captioning using Noise-Injected CLIP
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
We consider the task of image-captioning using only the CLIP model and additional text data at training time, and no additional captioned images.Our approach relies on the fact that CLIP is trained to make visual and textual embeddings similar.Therefore, we only need to learn how to translate CLIP textual embeddings back into text, and we can learn how to do this by learning a decoder for the frozen CLIP text encoder using only text.We argue that this intuition is "almost correct" because of a gap between the embedding spaces, and propose to rectify this via noise injection during training.We demonstrate the effectiveness of our approach by showing SOTA zero-shot image captioning across four benchmarks, including style transfer.Code, data, and models are available at https://github.com/DavidHuji/CapDec.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
Tan, H., & Bansal, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1514 · Cited by 2,319
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Lu, J., Batra, D., Parikh, D., & Lee, S. (2019) · arXiv · doi:10.48550/arxiv.1908.02265 · Cited by 2,109
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q. V., Sung, Y., Li, Z., & Duerig, T. (2021) · arXiv · doi:10.48550/arxiv.2102.05918 · Cited by 1,977
Microsoft COCO Captions: Data Collection and Evaluation Server
Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Dollar, P., & Zitnick, C. L. (2015) · arXiv · doi:10.48550/arxiv.1504.00325 · Cited by 1,614
Training with Noise is Equivalent to Tikhonov Regularization
Bishop, C. M. (1995) · Neural Computation · doi:10.1162/neco.1995.7.1.108 · Cited by 1,325
Unified Vision-Language Pre-Training for Image Captioning and VQA
Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., & Gao, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.7005 · Cited by 864
Cited by
AutoAD: Movie Description in Context
Han, T., Bain, M., Nagrani, A., Varol, G., Xie, W., & Zisserman, A. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01815 · Cited by 43
MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning
Zhang, C., Lin, K., Yang, Z., Wang, J., Li, L., Lin, C.-C., Liu, Z., & Wang, L. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01295 · Cited by 24
Metadata
- Authors
- Nukrai, D., Mokady, R., & Globerson, A.
- Venue
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Published
- 2022
- Pages
- 4055-4063
- OpenAlex
- W4385567053
- Cited by
- 85
- References
- 16
- FWCI
- 6.66
- Type
- conference paper
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Text-Only Training for Image Captioning using Noise-Injected CLIP. https://app.cochat.ai/papers/10.18653/v1/2022.findings-emnlp.299
- The paper
- Nukrai, D., Mokady, R., & Globerson, A. (2022). Text-Only Training for Image Captioning using Noise-Injected CLIP. Findings of the Association for Computational Linguistics: EMNLP 2022. https://doi.org/10.18653/v1/2022.findings-emnlp.299
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.