Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation [0.03%]
基于MMDiT的文本到图像模型的改进以生成同类主题图像
Tianyi Wei,Dongdong Chen,Yifan Zhou et al.
Tianyi Wei et al.
Representing the cutting-edge technique of text-to-image models, the latest Multimodal Diffusion Transformer (MMDiT) largely mitigates many generation issues existing in previous models. However, we discover that it still suffers from subje...
Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency [0.03%]
基于交叉领域几何一致性的VFM潜在空间中的偏置分布校准方法
Yanbiao Ma,Wei Dai,Zhiwu Lu et al.
Yanbiao Ma et al.
Despite the fast progress of deep learning, one standing challenge is the gap of the observed training samples and the underlying true distribution. There are multiple reasons for the causing of this gap e.g., sampling bias, noise etc. In t...
Hierarchical Information Embeddings with Neural ODEs for Personalized Federated Learning [0.03%]
基于神经ODE的层次信息嵌入的个性化 federated 学习方法
Rui She,Sijie Wang,Qiyu Kang et al.
Rui She et al.
Personalized federated learning (PFL) plays a pivotal role in ensuring efficient privacy preservation and secure collaborative learning. However, PFL faces significant challenges due to data heterogeneity and device diversity. To enhance pe...
FC$^{2}$: Fast Co-Clustering With Small-Scale Similarity Graph and Bipartite Graph Learning [0.03%]
基于小规模相似图和二分图学习的快速协同聚类算法
Xiaowei Zhao,Linrui Xie,Xiaojun Chang et al.
Xiaowei Zhao et al.
Bipartite graph-based co-clustering is efficient in modeling cluster manifold structures. However, existing methods decouple bipartite graph construction from the learning of pseudo-labels for samples and anchors, often leading to suboptima...
ASIL: Augmented Structural Information Learning for Deep Graph Clustering in Hyperbolic Space [0.03%]
用于双曲空间深度图聚类的增强结构信息学习（ASIL）
Li Sun,Zhenhao Huang,Yujie Wang et al.
Li Sun et al.
Graph clustering is a longstanding topic in machine learning. In recent years, deep learning methods have achieved encouraging results, but they still require predefined cluster numbers $K$, and typically struggle with imbalanced graphs, es...
Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization [0.03%]
基于语言指导和表征对齐的提示解耦以实现领域泛化
De Cheng,Zhipeng Xu,Xinyang Jiang et al.
De Cheng et al.
Domain Generalization (DG) seeks to develop models that perform well on unseen target domains by learning domain-invariant representations. Recent advances in pre-trained Visual Foundation Models (VFMs), such as CLIP, have shown strong pote...
Shiguang Wu,Yaqing Wang,Quanming Yao
Shiguang Wu
Making personalized recommendation for cold-start users, who only have a few interaction histories, is a challenging problem in recommendation systems. Recent works leverage hypernetworks to directly map interaction histories to user-specif...
Towards Real-world Holistic Privacy-Preserving Person Re-identification [0.03%]
面向真实世界的端到端行人重识别隐私保护方法
Qianxiang Meng,He Li,Min Cao et al.
Qianxiang Meng et al.
Real-world person re-identification (Re-ID) systems are susceptible to malicious attacks, leading to the leakage of pedestrian images and the Re-ID model, posing severe threats to the privacy of both system owners and pedestrians. Existing ...
Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation [0.03%]
广义正则化可信深度学习模型：理论与全面评估
Deep Shankar Pandey,Hyomin Choi,Qi Yu
Deep Shankar Pandey
Evidential deep learning (EDL) models, based on Subjective Logic, introduce a principled and computationally efficient way to make deterministic neural networks uncertainty-aware. The resulting evidential models can quantify fine-grained un...
Full-Scope Vectorization of Geographical Elements from Large-Size Remote Sensing Imagery [0.03%]
面向大规模遥感影像的地理要素全谱矢量化研究
Yansheng Li,Wanchun Li,Bo Dang et al.
Yansheng Li et al.
Large-size very-high-resolution (VHR) remote sensing imagery has emerged as a critical data source for high-precision vector mapping of multi-scale geographical elements such as building, water, road and etc. When dealing with the large-siz...