# Unifying Multimodal Transformer for Bi-directional Image and Text Generation

arXiv: https://arxiv.org/abs/2110.09753 · HTML: https://mlsanity.com/paper/2110.09753/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 19 Oct 2021.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [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)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [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)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)

## Built on by (most cited first, 30 of 41)

- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2307.05463/) (2023)
- [Language Models Can See: Plugging Visual Controls in Text Generation](https://mlsanity.com/paper/2205.02655/) (2022)
- [DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training](https://mlsanity.com/paper/2303.03032/) (2023)
- [CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment](https://mlsanity.com/paper/2209.06430/) (2022)
- [Visual Programming for Text-to-Image Generation and Evaluation](https://mlsanity.com/paper/2305.15328/) (2023)
- [Multimodal Image Synthesis and Editing: The Generative AI Era](https://mlsanity.com/paper/2112.13592/) (2021)
- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [UnIVAL: Unified Model for Image, Video, Audio and Language Tasks](https://mlsanity.com/paper/2307.16184/) (2023)
- [ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation](https://mlsanity.com/paper/2112.15283/) (2021)
- [Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model](https://mlsanity.com/paper/2312.12232/) (2023)
- [Unified Discrete Diffusion for Simultaneous Vision-Language Generation](https://mlsanity.com/paper/2211.14842/) (2022)
- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment](https://mlsanity.com/paper/2406.19255/) (2024)
- [Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models](https://mlsanity.com/paper/2308.16463/) (2023)
- [ToViLaG: Your Visual-Language Generative Model is Also An Evildoer](https://mlsanity.com/paper/2312.11523/) (2023)
- [Write and Paint: Generative Vision-Language Models are Unified Modal Learners](https://mlsanity.com/paper/2206.07699/) (2022)
- [OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models](https://mlsanity.com/paper/2212.04408/) (2022)
- [Guiding Image Captioning Models Toward More Specific Captions](https://mlsanity.com/paper/2307.16686/) (2023)
- [DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation](https://mlsanity.com/paper/2209.01339/) (2022)
- [CoBIT: A Contrastive Bi-directional Image-Text Generation Model](https://mlsanity.com/paper/2303.13455/) (2023)
- [Layout-Bridging Text-to-Image Synthesis](https://mlsanity.com/paper/2208.06162/) (2022)
- [Kinetic Typography Diffusion Model](https://mlsanity.com/paper/2407.10476/) (2024)
- [Vision + Language Applications: A Survey](https://mlsanity.com/paper/2305.14598/) (2023)
- [Multi-Modal Generative Embedding Model](https://mlsanity.com/paper/2405.19333/) (2024)
- [IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation](https://mlsanity.com/paper/2208.03431/) (2022)

## Abstract (arXiv)

We study the joint learning of image-to-text and text-to-image generations, which are naturally bi-directional tasks. Typical existing works design two separate task-specific models for each task, which impose expensive design efforts. In this work, we propose a unified image-and-text generative framework based on a single multimodal model to jointly study the bi-directional tasks. We adopt Transformer as our unified architecture for its strong performance and task-agnostic design. Specifically, we formulate both tasks as sequence generation tasks, where we represent images and text as unified sequences of tokens, and the Transformer learns multimodal interactions to generate sequences. We further propose two-level granularity feature representations and sequence-level training to improve the Transformer-based unified framework. Experiments show that our approach significantly improves previous Transformer-based model X-LXMERT's FID from 37.0 to 29.9 (lower is better) for text-to-image generation, and improves CIDEr-D score from 100.9% to 122.6% for fine-tuned image-to-text generation on the MS-COCO dataset. Our code is available online.