AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks
Spremljeno u:
| Izdano u: | arXiv.org (Dec 2, 2024), p. n/a |
|---|---|
| Glavni autor: | |
| Daljnji autori: | , |
| Izdano: |
Cornell University Library, arXiv.org
|
| Teme: | |
| Online pristup: | Citation/Abstract Full text outside of ProQuest |
| Oznake: |
Bez oznaka, Budi prvi tko označuje ovaj zapis!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3133540486 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 3133540486 | ||
| 045 | 0 | |b d20241202 | |
| 100 | 1 | |a Li, You | |
| 245 | 1 | |a AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks | |
| 260 | |b Cornell University Library, arXiv.org |c Dec 2, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a Diffusion models have recently been employed to generate high-quality images, reducing the need for manual data collection and improving model generalization in tasks such as object detection, instance segmentation, and image perception. However, the synthetic framework is usually designed with meticulous human effort for each task due to various requirements on image layout, content, and annotation formats, restricting the application of synthetic data on more general scenarios. In this paper, we propose AnySynth, a unified framework integrating adaptable, comprehensive, and highly controllable components capable of generating an arbitrary type of synthetic data given diverse requirements. Specifically, the Task-Specific Layout Generation Module is first introduced to produce reasonable layouts for different tasks by leveraging the generation ability of large language models and layout priors of real-world images. A Uni-Controlled Image Generation Module is then developed to create high-quality synthetic images that are controllable and based on the generated layouts. In addition, user specific reference images, and style images can be incorporated into the generation to task requirements. Finally, the Task-Oriented Annotation Module offers precise and detailed annotations for the generated images across different tasks. We have validated our framework's performance across various tasks, including Few-shot Object Detection, Cross-domain Object Detection, Zero-shot Composed Image Retrieval, and Multi-modal Image Perception and Grounding. The specific data synthesized by our framework significantly improves model performance in these tasks, demonstrating the generality and effectiveness of our framework. | |
| 653 | |a Large language models | ||
| 653 | |a Image segmentation | ||
| 653 | |a Image retrieval | ||
| 653 | |a Retrieval | ||
| 653 | |a Image annotation | ||
| 653 | |a Perception | ||
| 653 | |a Layouts | ||
| 653 | |a Controllability | ||
| 653 | |a Instance segmentation | ||
| 653 | |a Modules | ||
| 653 | |a Image quality | ||
| 653 | |a Object recognition | ||
| 653 | |a Image processing | ||
| 653 | |a Data collection | ||
| 653 | |a Synthetic data | ||
| 700 | 1 | |a Fan, Ma | |
| 700 | 1 | |a Yang, Yi | |
| 773 | 0 | |t arXiv.org |g (Dec 2, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3133540486/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2411.16749 |