# Self-Supervised Image Captioning with CLIP

arXiv: https://arxiv.org/abs/2306.15111 · HTML: https://mlsanity.com/paper/2306.15111/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 26 Jun 2023.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [Image Captioning: Transforming Objects into Words](https://mlsanity.com/paper/1906.05963/) (2019)
- [From Show to Tell: A Survey on Deep Learning-based Image Captioning](https://mlsanity.com/paper/2107.06912/) (2021)
- [From Captions to Visual Concepts and Back](https://mlsanity.com/paper/1411.4952/) (2014)
- [Dual-Level Collaborative Transformer for Image Captioning](https://mlsanity.com/paper/2101.06462/) (2021)
- [Fine-grained Image Captioning with CLIP Reward](https://mlsanity.com/paper/2205.13115/) (2022)
- [TIGEr: Text-to-Image Grounding for Image Caption Evaluation](https://mlsanity.com/paper/1909.02050/) (2019)
- [Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present](https://mlsanity.com/paper/1803.11439/) (2018)

## Built on by (most cited first, 3 of 3)

- [Pixels to Prose: Understanding the art of Image Captioning](https://mlsanity.com/paper/2408.15714/) (2024)
- [Emergent Natural Language with Communication Games for Improving Image Captioning Capabilities without Additional Data](https://mlsanity.com/paper/2507.08610/) (2025)
- [Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?](https://mlsanity.com/paper/2609.35020/) (2026)

## Abstract (arXiv)

Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which can be hard to obtain for many domains. To address this, we introduce a self-supervised image captioning method. After learning an initial signal from a small labeled dataset, our method transitions to self-supervised learning on unlabeled data, leveraging the auxiliary task of enhancing the CLIP relevance between images and generated captions. Remarkably, despite utilizing less than 2% of the labeled COCO dataset, our method delivers a performance comparable to state-of-the-art models trained on the complete dataset. Human evaluations further reveal that our method produces captions with greater distinctiveness and informativeness, two attributes inherently challenging to achieve through supervised learning.