Minchul Kim,Anil Jain,Xiaoming Liu
Minchul Kim
Over the past five decades, automated face recognition (FR) has progressed from handcrafted geometric and statistical approaches to advanced deep learning architectures that now approach, and in many cases exceed, human performance. This pa...
Soft Label Pruning and Quantization for Large-Scale Dataset Distillation [0.03%]
软标签剪枝和量化在大规模数据集提炼中的应用
Lingao Xiao,Yang He
Lingao Xiao
Large-scale dataset distillation requires storing auxiliary soft labels that can be 30-40× (ImageNet-1K) or 200× (ImageNet-21K) larger than the condensed images, undermining the goal of dataset compression. We identify two fundamental iss...
Yabin Wang,Zhiwu Huang,Zhou Su et al.
Yabin Wang et al.
The rise of AI-generated images has sparked serious concerns about their potential misuse across various domains, prompting the urgent need for robust detection methods. Despite advancements, many current approaches prioritize short-term ga...
Minggui Teng,Suhang Xuan,Zhiang Yan et al.
Minggui Teng et al.
Traditional cameras face limitations in maintaining focus across dynamic scenes, especially during rapid motion, due to the constraints of their lenses. Post-capture refocusing techniques, including deep learning-based methods and light fie...
Consistent and Controllable Image Animation with Motion Linear Diffusion Transformers [0.03%]
一致且可控的图像动画：运动线性扩散变压器方法
Xin Ma,Yaohui Wang,Genyun Jia et al.
Xin Ma et al.
Image animation has seen significant progress, driven by the powerful generative capabilities of diffusion models. However, maintaining appearance consistency with static input images and mitigating abrupt motion transitions in generated an...
Dual Adaptive Disentangled Representation Learning with Multimodal Data for Disease Diagnosis [0.03%]
基于多模态数据的疾病诊断的双重自适应解耦表示学习方法
Xiumei Chen,Wenliang Pan,Tao Wang et al.
Xiumei Chen et al.
The use of imaging and genetic data for biomarker detection and disease diagnosis can deepen the understanding of disease pathogenesis and assist in clinical diagnosis. However, current methods face two major challenges: 1) the significant ...
Learning From Each Other: Generalized Federated Incremental Semantic Segmentation [0.03%]
互学互助：泛化联合增量语义分割
Jiahua Dong,Wenqi Liang,Yang Cong et al.
Jiahua Dong et al.
Federated learning (FL) has advanced semantic segmentation through decentralized training to reduce annotation costs. However, most FL-based semantic segmentation methods assume fixed foreground classes, resulting in catastrophic forgetting...
Computational Investigation of Abstraction in Claude Monet's Water Lilies through Brushstroke Analysis [0.03%]
通过笔触分析计算克劳德·莫奈的《睡莲》中的抽象程度
Jia Li,Chaewan Chun,Kathryn Brown et al.
Jia Li et al.
Claude Monet's late paintings of Water Lilies exhibit stylistic transformations that are often characterized by art historians as increasingly abstract and gesturally expressive. However, it remains challenging to define and systematically ...
Out-of-Distribution-Resistant Evaluations for Explanations of Graph Neural Networks [0.03%]
图神经网络解释的分布外评估方法研究
Junfeng Fang,Hao Wu,An Zhang et al.
Junfeng Fang et al.
Explainability in Graph Neural Networks (GNNs) has shown considerable promise in bolstering their trustworthiness, credibility and transparency. Our research delves into the assessment of explainability within GNNs, a pivotal factor for ens...
DNGaussian++: Improving Sparse-View Gaussian Radiance Fields with Depth Normalization [0.03%]
基于深度归一化的稀疏视图高斯辐射场改进
Jiahe Li,Jiawei Zhang,Xiaohan Yu et al.
Jiahe Li et al.
Synthesizing novel views from sparse views has achieved impressive advances with radiance fields, yet prevailing methods suffer from high consumption or insufficient refinement capability. This paper introduces DNGaussian, a depth-regulariz...