# Text2Data: Low-Resource Data Generation with Textual Control

arXiv: https://arxiv.org/abs/2402.10941 · HTML: https://mlsanity.com/paper/2402.10941/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 55 references that are in the map.
- First posted on arXiv 8 Feb 2024.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Equivariant Diffusion for Molecule Generation in 3D](https://mlsanity.com/paper/2203.17003/) (2022)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://mlsanity.com/paper/2301.12661/) (2023)
- [MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation](https://mlsanity.com/paper/2205.09853/) (2022)
- [Diffsound: Discrete Diffusion Model for Text-to-sound Generation](https://mlsanity.com/paper/2207.09983/) (2022)
- [CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation](https://mlsanity.com/paper/2110.02624/) (2021)
- [A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios](https://mlsanity.com/paper/2010.12309/) (2020)
- [E(n) Equivariant Normalizing Flows](https://mlsanity.com/paper/2105.09016/) (2021)
- [SINE: SINgle Image Editing with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2212.04489/) (2022)
- [Video Generation From Text](https://mlsanity.com/paper/1710.00421/) (2017)
- [ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech](https://mlsanity.com/paper/2207.06389/) (2022)
- [Diffusion-SDF: Text-to-Shape via Voxelized Diffusion](https://mlsanity.com/paper/2212.03293/) (2022)
- [Talk-to-Edit: Fine-Grained Facial Editing via Dialog](https://mlsanity.com/paper/2109.04425/) (2021)

## Built on by (most cited first, 1 of 1)

- [Layering Virtual Try-On](https://mlsanity.com/paper/2607.22924/) (2026)

## Abstract (arXiv)

Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning community is investing considerable effort in generating data that is semantically coherent with textual instructions. While strides have been made in text-to-data generation spanning image editing, audio synthesis, video creation, and beyond, low-resource areas characterized by expensive annotations or complex data structures, such as molecules, motion dynamics, and time series, often lack textual labels. This deficiency impedes supervised learning, thereby constraining the application of advanced generative models for text-to-data tasks. In response to these challenges in the low-resource scenario, we propose Text2Data, a novel approach that utilizes unlabeled data to understand the underlying data distribution through an unsupervised diffusion model. Subsequently, it undergoes controllable finetuning via a novel constraint optimization-based learning objective that ensures controllability and effectively counteracts catastrophic forgetting. Comprehensive experiments demonstrate that Text2Data is able to achieve enhanced performance regarding controllability across various modalities, including molecules, motions and time series, when compared to existing baselines.