Gang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Gang Li has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Lingyu Si
Institute of Software, Chinese Academy of Sciences, Beijing, China
2 shared publications - Changwen Zheng
Institute of Software Chinese Academy of Sciences Beijing Beijing China
1 shared publication - Chongjian Ge1 shared publication
- Dan Xiao
Sichuan University
1 shared publication - Enze Xie
The University of Hong Kong, Hong Kong Hong Kong
1 shared publication - Fang Yang
School of Chemical Engineering, Hebei University of Technology, Tianjin, 300130, China
1 shared publication
Latest Publications
- 25 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 176
S2I-DiT: Unlocking the semantic-to-image transferability by fine-tuning large diffusion transformer models
- 25 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 176
S2I-DiT: Unlocking the semantic-to-image transferability by fine-tuning large diffusion transformer models
- Top Cited Papers
- 22 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
FreeStyle: Free lunch for text-guided style transfer using diffusion models
- 22 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
Top Cited PapersFreeStyle: Free lunch for text-guided style transfer using diffusion models
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11013-11021
DreamBooth++: Boosting Subject-Driven Generation via Region-Level References Packing
DreamBooth has demonstrated significant potential in subject-driven text-to-image generation, especially in scenarios requiring precise preservation of a subject's appearance. However, it still suffers from inefficiency and requires extensive iterative training to customize concepts using a small set of reference images. To address these issues, we introduce DreamBooth++, a region-level training strategy designed to significantly improve the efficiency and effectiveness of learning specific subjects. In particular, our approach employs a region-level data re-formulation technique that packs a set of reference images into a single sample, significantly reducing computational costs. Moreover, we adapt convolution and self-attention layers to ensure their processings are restricted within individual regions. Thus their operational scope (i.e., receptive field) can be preserved within a single subject, avoiding generating multiple sub-images within a single image. Last but not least, we design a text-guided prior regularization between our model and the pretrained one to preserve the original semantic generation ability. Comprehensive experiments demonstrate that our training strategy not only accelerates the subject-learning process but also significantly boosts fidelity to both subject and prompts in subject-driven generation.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11013-11021
Open AccessDreamBooth++: Boosting Subject-Driven Generation via Region-Level References Packing
DreamBooth has demonstrated significant potential in subject-driven text-to-image generation, especially in scenarios requiring precise preservation of a subject's appearance. However, it still suffers from inefficiency and requires extensive iterative training to customize concepts using a small set of reference images. To address these issues, we introduce DreamBooth++, a region-level training strategy designed to significantly improve the efficiency and effectiveness of learning specific subjects. In particular, our approach employs a region-level data re-formulation technique that packs a set of reference images into a single sample, significantly reducing computational costs. Moreover, we adapt convolution and self-attention layers to ensure their processings are restricted within individual regions. Thus their operational scope (i.e., receptive field) can be preserved within a single subject, avoiding generating multiple sub-images within a single image. Last but not least, we design a text-guided prior regularization between our model and the pretrained one to preserve the original semantic generation ability. Comprehensive experiments demonstrate that our training strategy not only accelerates the subject-learning process but also significantly boosts fidelity to both subject and prompts in subject-driven generation.
- 29 June 2018
- Published by Springer Nature in Colloid and Polymer Science
- Vol. 296 (8) , 1401-1407
Synthesis, characterization, and in vitro release analysis of a novel glucan-based polymer carrier
- 29 June 2018
- Published by Springer Nature in Colloid and Polymer Science
- Vol. 296 (8) , 1401-1407
Synthesis, characterization, and in vitro release analysis of a novel glucan-based polymer carrier