JLJun Lan

Jun Lan

*This is an algorithmically generated author record based on publicly available information.

Jun Lan has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking

    by Shuo Yang, Zijian Yu, Zhenzhe Ying, Yuqin Dai, Guoqing Wang, Jun Lan, Jinfeng Xu, Jinze Li, Edith C.H. Ngai


  • Open Access

    Generalizable and Adaptive Continual Learning Framework for AI-generated Image Detection

    by Hanyi Wang, Jun Lan, Yaoyu Kang, Huijia Zhu, Weiqiang Wang, Zhuosheng Zhang, Shilin Wang

    The malicious misuse and widespread dissemination of AI-generated images pose a significant threat to the authenticity of online information. Current detection methods often struggle to generalize to unseen generative models, and the rapid evolution of generative techniques continuously exacerbates this challenge. Without adaptability, detection models risk becoming ineffective in real-world applications. To address this critical issue, we propose a novel three-stage domain continual learning framework designed for continuous adaptation to evolving generative models. In the first stage, we employ a strategic parameter-efficient fine-tuning approach to develop a transferable offline detection model with strong generalization capabilities. Building upon this foundation, the second stage integrates unseen data streams into a continual learning process. To efficiently learn from limited samples of novel generated models and mitigate overfitting, we design a data augmentation chain with progressively increasing complexity. Furthermore, we leverage the Kronecker-Factored Approximate Curvature (K-FAC) method to approximate the Hessian and alleviate catastrophic forgetting. Finally, the third stage utilizes a linear interpolation strategy based on Linear Mode Connectivity, effectively capturing commonalities across diverse generative models and further enhancing overall performance. We establish a comprehensive benchmark of 27 generative models, including GANs, deepfakes, and diffusion models, chronologically structured up to August 2024 to simulate real-world scenarios. Extensive experiments demonstrate that our initial offline detectors surpass the leading baseline by +5.51% in terms of mean average precision. Our continual learning strategy achieves an average accuracy of 92.20%, outperforming state-of-the-art methods.


  • Open Access

    InterAnimate: Taming Region-Aware Diffusion Model for Realistic Human Interaction Animation

    by Yukang Lin, Yan Hong, Zunnan Xu, Xindi Li, Chao Xu, Chuanbiao Song, Ronghui Li, Haoxing Chen, Jun Lan, Huijia Zhu, et al.


  • Open Access

    Towards Explainable Fake Image Detection with Multi-Modal Large Language Models

    by Yikun Ji, Yan Hong, Jiahui Zhan, Haoxing Chen, Jun Lan, Huijia Zhu, Weiqiang Wang, Liqing Zhang, Jianfu Zhang


  • COIN-Matting: Confounder Intervention for Image Matting

    by Zhaohe Liao, Jiangtong Li, Jun Lan, Huijia Zhu, Weiqiang Wang, Li Niu, Liqing Zhang


  • ComFusion: Enhancing Personalized Generation by Instance-Scene Compositing and Fusion

    by Yan Hong, Yuxuan Duan, Bo Zhang, Haoxing Chen, Jun Lan, Huijia Zhu, Weiqiang Wang, Jianfu Zhang


  • Open Access

    Hierarchical Dynamic Image Harmonization

    by Haoxing Chen, Zhangxuan Gu, Yaohui Li, Jun Lan, Changhua Meng, Weiqiang Wang, Huaxiong Li

    Image harmonization is a critical task in computer vision, which aims to adjust the foreground to make it compatible with the background. Recent works mainly focus on using global transformations (i.e., normalization and color curve rendering) to achieve visual consistency. However, these models ignore local visual consistency and their huge model sizes limit their harmonization ability on edge devices. In this paper, we propose a hierarchical dynamic network (HDNet) to adapt features from local to global view for better feature transformation in efficient image harmonization. Inspired by the success of various dynamic models, local dynamic (LD) module and mask-aware global dynamic (MGD) module are proposed in this paper. Specifically, LD matches local representations between the foreground and background regions based on semantic similarities, then adaptively adjust every foreground local representation according to the appearance of its K-nearest neighbor background regions. In this way, LD can produce more realistic images at a more fine-grained level, and simultaneously enjoy the characteristic of semantic alignment. The MGD effectively applies distinct convolution to the foreground and background, learning the representations of foreground and background regions as well as their correlations to the global harmonization, facilitating local visual consistency for the images much more efficiently. Experimental results demonstrate that the proposed HDNet significantly reduces the total model parameters by more than 80% compared to previous methods, while still attaining state-of-the-art performance on the popular iHarmony4 dataset. Additionally, we introduced a lightweight version of HDNet, i.e., HDNet-lite, which has only 0.65MB parameters, yet it still achieve competitive performance. Our code is avaliable at https://github.com/chenhaoxing/HDNet.


  • Open Access

    Hierarchical Dynamic Image Harmonization

    by Haoxing Chen, Zhangxuan Gu, Yaohui Li, Jun Lan, Changhua Meng, Weiqiang Wang, Huaxiong Li

    Image harmonization is a critical task in computer vision, which aims to adjust the foreground to make it compatible with the background. Recent works mainly focus on using global transformations (i.e., normalization and color curve rendering) to achieve visual consistency. However, these models ignore local visual consistency and their huge model sizes limit their harmonization ability on edge devices. In this paper, we propose a hierarchical dynamic network (HDNet) to adapt features from local to global view for better feature transformation in efficient image harmonization. Inspired by the success of various dynamic models, local dynamic (LD) module and mask-aware global dynamic (MGD) module are proposed in this paper. Specifically, LD matches local representations between the foreground and background regions based on semantic similarities, then adaptively adjust every foreground local representation according to the appearance of its $K$-nearest neighbor background regions. In this way, LD can produce more realistic images at a more fine-grained level, and simultaneously enjoy the characteristic of semantic alignment. The MGD effectively applies distinct convolution to the foreground and background, learning the representations of foreground and background regions as well as their correlations to the global harmonization, facilitating local visual consistency for the images much more efficiently. Experimental results demonstrate that the proposed HDNet significantly reduces the total model parameters by more than 80\% compared to previous methods, while still attaining state-of-the-art performance on the popular iHarmony4 dataset. Notably, the HDNet achieves a 4\% improvement in PSNR and a 19\% reduction in MSE compared to the prior state-of-the-art methods.