ODIN: On-demand Data Formulation to Mitigate Dataset Lock-in
On the map: Diffusion models → Image generation, text-to-image and editing
Abstract (arXiv)
ODIN is an innovative approach that addresses the problem of dataset constraints by integrating generative AI models. Traditional zero-shot learning methods are constrained by the training dataset. To fundamentally overcome this limitation, ODIN attempts to mitigate the dataset constraints by generating on-demand datasets based on user requirements. ODIN consists of three main modules: a prompt generator, a text-to-image generator, and an image post-processor. To generate high-quality prompts and images, we adopted a large language model (e.g., ChatGPT), and a text-to-image diffusion model (e.g., Stable Diffusion), respectively. We evaluated ODIN on various datasets in terms of model accuracy and data diversity to demonstrate its potential, and conducted post-experiments for further investigation. Overall, ODIN is a feasible approach that enables Al to learn unseen knowledge beyond the training dataset.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 22 of its 39 references that are in the map. First posted on arXiv 13 Mar 2023.
Builds on
22 of 39 references.
References · 22
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
- 2021Zero-Shot Text-to-Image Generationcited by 4,276
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
- 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
- 2020Designing Network Design Spacescited by 954
10 more
- 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 225
- 2020A Review of Generalized Zero-Shot Learning Methodscited by 159
- 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
- 2019This dataset does not exist: training models from generated imagescited by 65
- 2020UniformAugment: A Search-free Probabilistic Data Augmentation Approachcited by 38
- 2018Preserving Semantic Relations for Zero-Shot Learningcited by 35
- 2019ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translationcited by 9
- 2021Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentationcited by 7
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot
- 2024VILA2: VILA Augmented VILA
- 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models
- 2025BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation
- 2023Reinforcement Learning for Generative AI: A Survey
- 2025Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications
- 2024Controlled Training Data Generation with Diffusion Models
- 2024Better Synthetic Data by Retrieving and Transforming Existing Datasets