24 citations · 65 across the 29 of their papers we have counts for
33 papers
DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling
Zheyuan Zhan, Can Wang, Jiawei Chen +4
Flow-based image editing (FlowEdit) enables inversion-free semantic changes through the difference between source and target velocities. In this paper, we observe that FlowEdit's d…
Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models
Hongxin Xu, Jianping Mei, Can Wang +1
Coverless image steganography (CIS) synthesizes a stego image rather than modifying an existing cover image, enabling authorized recipients to reconstruct the original secret image…
Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editing
Zheyuan Zhan, Hongchen Li, Can Wang +6
Inversion-based image editing offers flexible and training-free control but still struggles with inversion accuracy and the trade-off between editing fidelity and background preser…
Analyzing and Improving Fast Sampling of Text-to-Image Diffusion Models
Zhenyu Zhou, Defang Chen, Siwei Lyu +2
Text-to-image diffusion models have achieved unprecedented success but still struggle to produce high-quality results under limited sampling budgets. Existing training-free samplin…
Geometric Regularity in Deterministic Sampling Dynamics of Diffusion-based Generative Models
Defang Chen, Zhenyu Zhou, Can Wang +1
Diffusion-based generative models employ stochastic differential equations (SDEs) and their equivalent probability flow ordinary differential equations (ODEs) to establish a smooth…
Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges
Qijie Xu, Can Wang, Jiawei Chen +2
Recent advances in visual generative models have enabled the creation of highly realistic, fully AI-generated images without relying on real source content. While beneficial for ma…
DICE: Distilling Classifier-Free Guidance into Text Embeddings
Zhenyu Zhou, Defang Chen, Can Wang +2
Text-to-image diffusion models are capable of generating high-quality images, but suboptimal pre-trained text representations often result in these images failing to align closely…
Simple and Fast Distillation of Diffusion Models
Zhenyu Zhou, Defang Chen, Can Wang +2
Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient…
Conditional Image Synthesis with Diffusion Models: A Survey
Zheyuan Zhan, Defang Chen, Jian-Ping Mei +5
Conditional image synthesis based on user-specified requirements is a key component in creating complex visual content. In recent years, diffusion-based generative modeling has bec…
Knowledge Distillation with Refined Logits
Wujie Sun, Defang Chen, Siwei Lyu +3
Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this pap…
On the Trajectory Regularity of ODE-based Diffusion Sampling
Defang Chen, Zhenyu Zhou, Can Wang +2
Diffusion-based generative models use stochastic differential equations (SDEs) and their equivalent ordinary differential equations (ODEs) to establish a smooth connection between…
Knowledge Translation: A New Pathway for Model Compression
Wujie Sun, Defang Chen, Jiawei Chen +3
Deep learning has witnessed significant advancements in recent years at the cost of increasing training, inference, and model storage overhead. While existing model compression met…
Fast ODE-based Sampling for Diffusion Models in Around 5 Steps
Zhenyu Zhou, Defang Chen, Can Wang +1
Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs), with the aim of obtaining an accurate solution with as few number…
Customizing Synthetic Data for Data-Free Student Learning
Shiya Luo, Defang Chen, Can Wang
Data-free knowledge distillation (DFKD) aims to obtain a lightweight student model without original training data. Existing works generally synthesize data from the pre-trained tea…
Adaptive Multi-Teacher Knowledge Distillation with Meta-Learning
Hailin Zhang, Defang Chen, Can Wang
Multi-Teacher knowledge distillation provides students with additional supervision from multiple pre-trained teachers with diverse information sources. Most existing methods explor…
A Geometric Perspective on Diffusion Models
Defang Chen, Zhenyu Zhou, Jian-Ping Mei +3
Recent years have witnessed significant progress in developing effective training and fast sampling techniques for diffusion models. A remarkable advancement is the use of stochast…
Accelerating Diffusion Sampling with Classifier-based Feature Distillation
Wujie Sun, Defang Chen, Can Wang +3
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distill…
Online Cross-Layer Knowledge Distillation on Graph Neural Networks with Deep Supervision
Jiongyu Guo, Defang Chen, Can Wang
Graph neural networks (GNNs) have become one of the most popular research topics in both academia and industry communities for their strong ability in handling irregular graph data…
Label-Efficient Domain Generalization via Collaborative Exploration and Generalization
Junkun Yuan, Xu Ma, Defang Chen +3
Considerable progress has been made in domain generalization (DG) which aims to learn a generalizable model from multiple well-annotated source domains to unknown target domains. H…
Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding
Yichen Liu, Jiawei Chen, Defang Chen +3
Knowledge Graph Embedding (KGE), which projects entities and relations into continuous vector spaces, has garnered significant attention. Although high-dimensional KGE methods offe…
Alignahead: Online Cross-Layer Knowledge Extraction on Graph Neural Networks
Jiongyu Guo, Defang Chen, Can Wang
Existing knowledge distillation methods on graph neural networks (GNNs) are almost offline, where the student model extracts knowledge from a powerful teacher model to improve its…
Knowledge Distillation with the Reused Teacher Classifier
Defang Chen, Jian-Ping Mei, Hailin Zhang +3
Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various ap…
Confidence-Aware Multi-Teacher Knowledge Distillation
Hailin Zhang, Defang Chen, Can Wang
Knowledge distillation is initially introduced to utilize additional supervision from a single teacher model for the student model training. To boost the student performance, some…
Knowledge Distillation with Deep Supervision
Shiya Luo, Defang Chen, Can Wang
Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the tradi…