# Exploring Discrete Diffusion Models for Image Captioning

arXiv: https://arxiv.org/abs/2211.11694 · HTML: https://mlsanity.com/paper/2211.11694/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 71 of its 81 references that are in the map.
- First posted on arXiv 21 Nov 2022.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 71)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)

## Built on by (most cited first, 16 of 16)

- [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://mlsanity.com/paper/2303.09556/) (2023)
- [Any-to-Any Generation via Composable Diffusion](https://mlsanity.com/paper/2305.11846/) (2023)
- [Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --](https://mlsanity.com/paper/2301.03362/) (2023)
- [PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model](https://mlsanity.com/paper/2306.02531/) (2023)
- [Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning](https://mlsanity.com/paper/2309.02999/) (2023)
- [DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer](https://mlsanity.com/paper/2303.03755/) (2023)
- [Guiding Image Captioning Models Toward More Specific Captions](https://mlsanity.com/paper/2307.16686/) (2023)
- [IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition](https://mlsanity.com/paper/2312.11923/) (2023)
- [LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?](https://mlsanity.com/paper/2404.10763/) (2024)
- [Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning](https://mlsanity.com/paper/2309.04965/) (2023)
- [DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism](https://mlsanity.com/paper/2311.14920/) (2023)
- [Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image](https://mlsanity.com/paper/2410.15312/) (2024)
- [Generalized Visual Relation Detection with Diffusion Models](https://mlsanity.com/paper/2504.12100/) (2025)
- [Diffusion Is Your Friend in Show, Suggest and Tell](https://mlsanity.com/paper/2512.10038/) (2025)
- [CrossTrafficLLM: A Human-Centric Framework for Interpretable Traffic Intelligence via Large Language Model](https://mlsanity.com/paper/2601.06042/) (2025)
- [Learning from Multimodal Pseudo-Labels for Robust Open-Vocabulary Instance and Panoptic Segmentation](https://mlsanity.com/paper/2608.11681/) (2026)

## Abstract (arXiv)

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image generation, where the output is continuous and redundant with a fixed length, texts in image captions are categorical and short with varied lengths. Therefore, naively applying the discrete diffusion model to text decoding does not work well, as shown in our experiments. To address the performance gap, we propose several key techniques including best-first inference, concentrated attention mask, text length prediction, and image-free training. On COCO without additional caption pre-training, it achieves a CIDEr score of 117.8, which is +5.0 higher than the auto-regressive baseline with the same architecture in the controlled setting. It also performs +26.8 higher CIDEr score than the auto-regressive baseline (230.3 v.s.203.5) on a caption infilling task. With 4M vision-language pre-training images and the base-sized model, we reach a CIDEr score of 125.1 on COCO, which is competitive to the best well-developed auto-regressive frameworks. The code is available at https://github.com/buxiangzhiren/DDCap.