10 code implementations • 21 Jun 2017 • Ahmed Elgammal, Bingchen Liu, Mohamed Elhoseiny, Marian Mazzone
We argue that such networks are limited in their ability to generate creative products in their original design.
no code implementations • CVPR 2018 • Yizhe Zhu, Mohamed Elhoseiny, Bingchen Liu, Xi Peng, Ahmed Elgammal
Most existing zero-shot learning methods consider the problem as a visual semantic embedding one.
no code implementations • 23 Jan 2018 • Ahmed Elgammal, Marian Mazzone, Bingchen Liu, Diana Kim, Mohamed Elhoseiny
How does the machine classify styles in art?
1 code implementation • ICCV 2019 • Yizhe Zhu, Jianwen Xie, Bingchen Liu, Ahmed Elgammal
We investigate learning feature-to-feature translator networks by alternating back-propagation as a general-purpose solution to zero-shot learning (ZSL) problems.
1 code implementation • 26 May 2019 • Bingchen Liu, Yizhe Zhu, Zuohui Fu, Gerard de Melo, Ahmed Elgammal
Exploring the potential of GANs for unsupervised disentanglement learning, this paper proposes a novel GAN-based disentanglement framework with One-Hot Sampling and Orthogonal Regularization (OOGAN).
1 code implementation • 26 Feb 2020 • Bingchen Liu, Kunpeng Song, Ahmed Elgammal
We propose a new approach for synthesizing fully detailed art-stylized images from sketches.
no code implementations • 27 May 2020 • Bingchen Liu, Kunpeng Song, Yizhe Zhu, Gerard de Melo, Ahmed Elgammal
Focusing on text-to-image (T2I) generation, we propose Text and Image Mutual-Translation Adversarial Networks (TIME), a lightweight but effective model that jointly learns a T2I generator G and an image captioning discriminator D under the Generative Adversarial Network framework.
1 code implementation • 16 Dec 2020 • Bingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal
Moreover, with the proposed sketch generator, the model shows a promising performance on style mixing and style transfer, which require synthesized images to be both style-consistent and semantically meaningful.
7 code implementations • ICLR 2021 • Bingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal
Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images.
Ranked #2 on Image Generation on ADE-Indoor
no code implementations • 29 Sep 2021 • Bingchen Liu, Yizhe Zhu, Xiao Yang, Ahmed Elgammal
The VQSN module facilitates a more delicate separation of posture and identity, while the training scheme ensures the VQSN module learns the pose-related representations.
1 code implementation • CVPR 2023 • Yufan Zhou, Bingchen Liu, Yizhe Zhu, Xiao Yang, Changyou Chen, Jinhui Xu
Unlike the baseline diffusion model used in DALL-E 2, our method seamlessly encodes prior knowledge of the pre-trained CLIP model in its diffusion process by designing a new initialization distribution and a new transition step of the diffusion.
Ranked #3 on Text-to-Image Generation on Multi-Modal-CelebA-HQ
no code implementations • 8 Dec 2022 • Kunpeng Song, Ligong Han, Bingchen Liu, Dimitris Metaxas, Ahmed Elgammal
Can a text-to-image diffusion model be used as a training objective for adapting a GAN generator to another domain?
1 code implementation • 15 May 2023 • Shanchuan Lin, Bingchen Liu, Jiashi Li, Xiao Yang
We discover that common diffusion noise schedules do not enforce the last timestep to have zero signal-to-noise ratio (SNR), and some implementations of diffusion samplers do not start from the last timestep.
no code implementations • 25 Oct 2023 • Bingchen Liu, Shihao Hou, Weixin Zeng, Xiang Zhao, Shijun Liu, Li Pan
MulCanon unifies the learning objectives of diffusion model, KGE and clustering algorithms, and adopts a two-step multi-task learning paradigm for training.
no code implementations • 13 Mar 2024 • Bingchen Liu, Yuanyuan Fang
However, it is challenging to maintain the performance of KG embedding models while forgetting the influence of specific forgotten data on the model.
no code implementations • 21 Mar 2024 • Bingchen Liu, Huang Peng, Weixin Zeng, Xiang Zhao, Shijun Liu, Li Pan
MulCanon unifies the learning objectives of these sub-tasks, and adopts a two-stage multi-task learning paradigm for training.
1 code implementation • 8 Apr 2024 • Kunpeng Song, Yizhe Zhu, Bingchen Liu, Qing Yan, Ahmed Elgammal, Xiao Yang
This approach effectively synergizes reference image and text prompt information to produce valuable image features, facilitating an image diffusion model.