210 citations · 1k across the 55 of their papers we have counts for
57 papers
Leveraging Hierarchical Image-Text Misalignment for Universal Fake Image Detection
Daichi Zhang, Tong Zhang, Jianmin Bao +2
With the rapid development of generative models, detecting generated fake images to prevent their malicious use has become a critical issue recently. Existing methods frame this ch…
HairShifter: Consistent and High-Fidelity Video Hair Transfer via Anchor-Guided Animation
Wangzheng Shi, Yinglin Zheng, Yuxin Lin +3
Hair transfer is increasingly valuable across domains such as social media, gaming, advertising, and entertainment. While significant progress has been made in single-image hair tr…
Fast Autoregressive Models for Continuous Latent Generation
Tiankai Hang, Jianmin Bao, Fangyun Wei +1
Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents si…
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Microsoft, :, Abdelrahman Abouelenin +73
We introduce Phi-4-Mini and Phi-4-Multimodal, compact yet highly capable language and multimodal models. Phi-4-Mini is a 3.8-billion-parameter language model trained on high-qualit…
DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models
Zhendong Wang, Jianmin Bao, Shuyang Gu +3
In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions. A primary challenge lies in…
Diffusion Models without Classifier-free Guidance
Zhicong Tang, Jianmin Bao, Dong Chen +1
This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovati…
SmartEraser: Remove Anything from Images using Masked-Region Guidance
Longtao Jiang, Zhendong Wang, Jianmin Bao +5
Object removal has so far been dominated by the mask-and-inpaint paradigm, where the masked region is excluded from the input, leaving models relying on unmasked areas to inpaint t…
SynChart: Synthesizing Charts from Language Models
Mengchen Liu, Qixiu Li, Dongdong Chen +3
With the release of GPT-4V(O), its use in generating pseudo labels for multi-modality tasks has gained significant popularity. However, it is still a secret how to build such advan…
Improved Noise Schedule for Diffusion Training
Tiankai Hang, Shuyang Gu, Xin Geng +1
Diffusion models have emerged as the de facto choice for generating high-quality visual signals across various domains. However, training a single model to predict noise across var…
Towards More Unified In-context Visual Understanding
Dianmo Sheng, Dongdong Chen, Zhentao Tan +7
The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domai…
PersonMAE: Person Re-Identification Pre-Training with Masked AutoEncoders
Hezhen Hu, Xiaoyi Dong, Jianmin Bao +4
Pre-training is playing an increasingly important role in learning generic feature representation for Person Re-identification (ReID). We argue that a high-quality ReID representat…
InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
Zigang Geng, Binxin Yang, Tiankai Hang +8
We present InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions. Unlike existing approaches that integrate prior knowledge…
AltFreezing for More General Video Face Forgery Detection
Zhendong Wang, Jianmin Bao, Wengang Zhou +2
Existing face forgery detection models try to discriminate fake images by detecting only spatial artifacts (e.g., generative artifacts, blending) or mainly temporal artifacts (e.g.…
HQ-50K: A Large-scale, High-quality Dataset for Image Restoration
Qinhong Yang, Dongdong Chen, Zhentao Tan +6
This paper introduces a new large-scale image restoration dataset, called HQ-50K, which contains 50,000 high-quality images with rich texture details and semantic diversity. We ana…
Designing a Better Asymmetric VQGAN for StableDiffusion
Zixin Zhu, Xuelu Feng, Dongdong Chen +5
StableDiffusion is a revolutionary text-to-image generator that is causing a stir in the world of image generation and editing. Unlike traditional methods that learn a diffusion mo…
Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
Shihao Zhao, Dongdong Chen, Yen-Chun Chen +4
Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. How…
CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning
Yiting Cheng, Fangyun Wei, Jianmin Bao +2
This work focuses on sign language retrieval-a recently proposed task for sign language understanding. Sign language retrieval consists of two sub-tasks: text-to-sign-video (T2V) r…
DIRE for Diffusion-Generated Image Detection
Zhendong Wang, Jianmin Bao, Wengang Zhou +4
Diffusion models have shown remarkable success in visual synthesis, but have also raised concerns about potential abuse for malicious purposes. In this paper, we seek to build a de…
Efficient Diffusion Training via Min-SNR Weighting Strategy
Tiankai Hang, Shuyang Gu, Chen Li +5
Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered th…
CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
Xiaoyi Dong, Jianmin Bao, Ting Zhang +7
Recent studies have shown that CLIP has achieved remarkable success in performing zero-shot inference while its fine-tuning performance is not satisfactory. In this paper, we ident…
Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion
Tengfei Wang, Bo Zhang, Ting Zhang +8
This paper presents a 3D generative model that uses diffusion models to automatically generate 3D digital avatars represented as neural radiance fields. A significant challenge in…
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
Hanqing Zhao, Dianmo Sheng, Jianmin Bao +9
Copy-Paste is a simple and effective data augmentation strategy for instance segmentation. By randomly pasting object instances onto new background images, it creates new training…
CLIP2GAN: Towards Bridging Text with the Latent Space of GANs
Yixuan Wang, Wengang Zhou, Jianmin Bao +3
In this work, we are dedicated to text-guided image generation and propose a novel framework, i.e., CLIP2GAN, by leveraging CLIP model and StyleGAN. The key idea of our CLIP2GAN is…
SinDiffusion: Learning a Diffusion Model from a Single Natural Image
Weilun Wang, Jianmin Bao, Wengang Zhou +4
We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image. SinDiffusion significantly improves the qual…