# Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training

arXiv: https://arxiv.org/abs/2401.02347 · HTML: https://mlsanity.com/paper/2401.02347/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 51 references that are in the map.
- First posted on arXiv 4 Jan 2024.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [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)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Understanding the Behaviour of Contrastive Loss](https://mlsanity.com/paper/2012.09740/) (2020)
- [Visual Dialog](https://mlsanity.com/paper/1611.08669/) (2016)
- [How Much Can CLIP Benefit Vision-and-Language Tasks?](https://mlsanity.com/paper/2107.06383/) (2021)
- [GLIPv2: Unifying Localization and Vision-Language Understanding](https://mlsanity.com/paper/2206.05836/) (2022)
- [Exploring Visual Relationship for Image Captioning](https://mlsanity.com/paper/1809.07041/) (2018)

## Built on by (most cited first, 12 of 12)

- [Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation](https://mlsanity.com/paper/2504.09480/) (2025)
- [NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation](https://mlsanity.com/paper/2510.21122/) (2025)
- [DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations](https://mlsanity.com/paper/2601.00623/) (2026)
- [Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum](https://mlsanity.com/paper/2603.05256/) (2026)
- [Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis](https://mlsanity.com/paper/2408.04909/) (2024)
- [Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction](https://mlsanity.com/paper/2512.04309/) (2025)
- [EFDiT: Efficient Fine-grained Image Generation Using Diffusion Transformer Models](https://mlsanity.com/paper/2512.05152/) (2025)
- [WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition](https://mlsanity.com/paper/2603.09921/) (2026)
- [Beyond the Linear Separability Ceiling: Aligning Representations in VLMs](https://mlsanity.com/paper/2507.07574/) (2025)
- [Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling](https://mlsanity.com/paper/2511.07710/) (2025)
- [Caption Generation for Dongba Paintings via Prompt Learning and Semantic Fusion](https://mlsanity.com/paper/2603.22946/) (2026)
- [Generative Retrieval for Unsupervised Text-Based Person Search](https://mlsanity.com/paper/2609.12965/) (2026)

## Abstract (arXiv)

Image captioning aims at generating descriptive and meaningful textual descriptions of images, enabling a broad range of vision-language applications. Prior works have demonstrated that harnessing the power of Contrastive Image Language Pre-training (CLIP) offers a promising approach to achieving zero-shot captioning, eliminating the need for expensive caption annotations. However, the widely observed modality gap in the latent space of CLIP harms the performance of zero-shot captioning by breaking the alignment between paired image-text features. To address this issue, we conduct an analysis on the CLIP latent space which leads to two findings. Firstly, we observe that the CLIP's visual feature of image subregions can achieve closer proximity to the paired caption due to the inherent information loss in text descriptions. In addition, we show that the modality gap between a paired image-text can be empirically modeled as a zero-mean Gaussian distribution. Motivated by the findings, we propose a novel zero-shot image captioning framework with text-only training to reduce the modality gap. In particular, we introduce a subregion feature aggregation to leverage local region information, which produces a compact visual representation for matching text representation. Moreover, we incorporate a noise injection and CLIP reranking strategy to boost captioning performance. We also extend our framework to build a zero-shot VQA pipeline, demonstrating its generality. Through extensive experiments on common captioning and VQA datasets such as MSCOCO, Flickr30k and VQAV2, we show that our method achieves remarkable performance improvements. Code is available at https://github.com/Artanic30/MacCap.