Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generation

• URL: http://arxiv.org/abs/2406.09305v2
• Date: Wed, 7 Aug 2024 23:45:13 GMT
• Title: Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generation
• Authors: Yufan Zhou, Ruiyi Zhang, Kaizhi Zheng, Nanxuan Zhao, Jiuxiang Gu, Zichao Wang, Xin Eric Wang, Tong Sun,
• Abstract summary: We construct the first large-scale dataset for subject-driven image editing and generation. Our dataset is 5 times the size of previous largest dataset, yet our cost is tens of thousands of GPU hours lower.
• Score: 58.09421301921607
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In subject-driven text-to-image generation, recent works have achieved superior performance by training the model on synthetic datasets containing numerous image pairs. Trained on these datasets, generative models can produce text-aligned images for specific subject from arbitrary testing image in a zero-shot manner. They even outperform methods which require additional fine-tuning on testing images. However, the cost of creating such datasets is prohibitive for most researchers. To generate a single training pair, current methods fine-tune a pre-trained text-to-image model on the subject image to capture fine-grained details, then use the fine-tuned model to create images for the same subject based on creative text prompts. Consequently, constructing a large-scale dataset with millions of subjects can require hundreds of thousands of GPU hours. To tackle this problem, we propose Toffee, an efficient method to construct datasets for subject-driven editing and generation. Specifically, our dataset construction does not need any subject-level fine-tuning. After pre-training two generative models, we are able to generate infinite number of high-quality samples. We construct the first large-scale dataset for subject-driven image editing and generation, which contains 5 million image pairs, text prompts, and masks. Our dataset is 5 times the size of previous largest dataset, yet our cost is tens of thousands of GPU hours lower. To test the proposed dataset, we also propose a model which is capable of both subject-driven image editing and generation. By simply training the model on our proposed dataset, it obtains competitive results, illustrating the effectiveness of the proposed dataset construction framework.

Related papers

• DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models [61.906934570771256]
  We present a generic dataset generation model that can produce diverse synthetic images and perception annotations. Our method builds upon the pre-trained diffusion model and extends text-guided image synthesis to perception data generation. We show that the rich latent code of the diffusion model can be effectively decoded as accurate perception annotations using a decoder module.
  arXiv  Detail & Related papers  (2023-08-11T14:38:11Z)
• Evaluating Data Attribution for Text-to-Image Models [62.844382063780365]
  We evaluate attribution through "customization" methods, which tune an existing large-scale model toward a given exemplar object or style. Our key insight is that this allows us to efficiently create synthetic images that are computationally influenced by the exemplar by construction. By taking into account the inherent uncertainty of the problem, we can assign soft attribution scores over a set of training images.
  arXiv  Detail & Related papers  (2023-06-15T17:59:51Z)
• HADA: A Graph-based Amalgamation Framework in Image-text Retrieval [2.3013879633693266]
  We propose a compact graph-based framework, named HADA, which can combine pretrained models to produce a better result. Our experiments showed that HADA could increase baseline performance by more than 3.6% in terms of evaluation metrics in the Flickr30k dataset.
  arXiv  Detail & Related papers  (2023-01-11T22:25:20Z)
• Weakly Supervised Annotations for Multi-modal Greeting Cards Dataset [8.397847537464534]
  We propose to aggregate features from pretrained images and text embeddings to learn abstract visual concepts from Greeting Cards dataset. The proposed dataset is also useful for generating greeting card images using pre-trained text-to-image generation model.
  arXiv  Detail & Related papers  (2022-12-01T20:07:52Z)
• Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel Logistics [58.720142291102135]
  We present a fully automated pipeline to generate a synthetic dataset for instance segmentation in four steps. We first scrape images for the objects of interest from popular image search engines. We compare three different methods for image selection: Object-agnostic pre-processing, manual image selection and CNN-based image selection.
  arXiv  Detail & Related papers  (2022-10-18T12:49:04Z)
• KNN-Diffusion: Image Generation via Large-Scale Retrieval [40.6656651653888]
  Learning to adapt enables several new capabilities. Fine-tuning trained models to new samples can be achieved by simply adding them to the table. Our diffusion-based model trains on images only, by leveraging a joint Text-Image multi-modal metric.
  arXiv  Detail & Related papers  (2022-04-06T14:13:35Z)
• WuDaoMM: A large-scale Multi-Modal Dataset for Pre-training models [2.603259641572195]
  We introduce a large-scale multi-modal corpora named WuDaoMM, totally containing more than 650M image-text pairs. About 600 million pairs of data are collected from multiple webpages in which image and caption present weak correlation. We also release a base version of WuDaoMM with 5 million strong-correlated image-text pairs, which is sufficient to support the common cross-modal model pre-training.
  arXiv  Detail & Related papers  (2022-03-22T06:12:20Z)
• LAFITE: Towards Language-Free Training for Text-to-Image Generation [83.2935513540494]
  We propose the first work to train text-to-image generation models without any text data. Our method leverages the well-aligned multi-modal semantic space of the powerful pre-trained CLIP model. We obtain state-of-the-art results in the standard text-to-image generation tasks.
  arXiv  Detail & Related papers  (2021-11-27T01:54:45Z)
• DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort [117.41383937100751]
  Current deep networks are extremely data-hungry, benefiting from training on large-scale datasets. We show how the GAN latent code can be decoded to produce a semantic segmentation of the image. These generated datasets can then be used for training any computer vision architecture just as real datasets are.
  arXiv  Detail & Related papers  (2021-04-13T20:08:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.