Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers

1 code implementation • 9 May 2024 • Peng Gao, Le Zhuo, Dongyang Liu, Ruoyi Du, Xu Luo, Longtian Qiu, Yuhang Zhang, Chen Lin, Rongjie Huang, Shijie Geng, Renrui Zhang, Junlin Xi, Wenqi Shao, Zhengkai Jiang, Tianshuo Yang, Weicai Ye, He Tong, Jingwen He, Yu Qiao, Hongsheng Li

Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details.

Triplet Knowledge Distillation

no code implementations • 25 May 2023 • Xijun Wang, Dongyang Liu, Meina Kan, Chunrui Han, Zhongqin Wu, Shiguang Shan

Distillation then begins in an online manner, and the teacher is only allowed to express solutions within the aforementioned subspace.

Face Recognition Image Classification +1

Function-Consistent Feature Distillation

1 code implementation • 24 Apr 2023 • Dongyang Liu, Meina Kan, Shiguang Shan, Xilin Chen

The core idea of FCFD is to make teacher and student features not only numerically similar, but more importantly produce similar outputs when fed to the later part of the same network.

Image Classification object-detection +1

Give Me Something to Eat: Referring Expression Comprehension with Commonsense Knowledge

1 code implementation • 2 Jun 2020 • Peng Wang, Dongyang Liu, Hui Li, Qi Wu

In this case, we need to use commonsense knowledge to identify the objects in the image.

16k Referring Expression +1