D2S-RSG-SSD: Dual Double-Sampling with Random Sub-Samples Generation for Self-Supervised Real Image Denoising [0.03%]
基于自监督随机子样本生成的双重采样图像去噪方法
Xiao Liu,Xiuya Shi,Yizhong Pan et al.
Xiao Liu et al.
Recent advances in self-supervised image denoising have highlighted the potential of Blind-Spot Networks (BSNs). However, existing methods suffer from three major limitations: (1) Their effectiveness in real-world scenarios is limited by st...
FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction [0.03%]
FreeSplat++：用于高效室内场景重建的通用3D高斯点刻技术
Yunsong Wang,Tianxin Huang,Hanlin Chen et al.
Yunsong Wang et al.
Recently, the integration of the efficient feed-forward scheme into 3D Gaussian Splatting (3DGS) has been actively explored. However, most existing methods focus on sparse view reconstruction of small regions and cannot produce eligible who...
Safe Fairness Guarantees Without Demographics in Classification: Spectral Uncertainty Set Perspective [0.03%]
无需人口统计信息的分类公平性保证：谱不确定集合视角
Ainhize Barrainkua,Santiago Mazuelas,Novi Quadrianto et al.
Ainhize Barrainkua et al.
As automated classification systems become increasingly prevalent, concerns have emerged over their potential to reinforce and amplify existing societal biases. In the light of this issue, many methods have been proposed to enhance the fair...
Wei Huang,Yue Liao,Yukang Chen et al.
Wei Huang et al.
Mixture-of-Experts (MoE) has emerged as an effective and efficient scaling mechanism for large language models (LLMs) and vision-language models (VLMs). By expanding a single feed-forward network into multiple expert branches, MoE increases...
FlowTurbo: Accelerating Flow-based Image Generation Models via Multi-stage Refinement [0.03%]
FlowTurbo：通过多阶段细化加速基于流的图像生成模型
Wenliang Zhao,Minglei Shi,Xumin Yu et al.
Wenliang Zhao et al.
Building on the success of diffusion models in visual generation, flow-based models reemerge as another prominent family of generative models that have achieved competitive or better performance in terms of both visual quality and inference...
Tail Task Risk Minimization in Meta-Learning from Theoretical Advances to Practical Strategies [0.03%]
从理论进展到实用策略：元学习中的尾部任务风险最小化问题研究
Yiqin Lv,Dong Liang,Wumei Du et al.
Yiqin Lv et al.
Meta learning is a promising paradigm in the era of large models, and task distributional robustness has become an indispensable consideration in real-world scenarios. Recent advances have examined the effectiveness of tail task risk minimi...
DOtA++: Unsupervisely and Collaboratively Detect Objects From Multi-Agent Observations With Multi-Modal Prior Constraints [0.03%]
基于多智能体观测和多模态先验约束的无监督协作目标检测算法DOTA++
Qiming Xia,Longhui Zheng,Shijia Zhao et al.
Qiming Xia et al.
Enhancing perception performance via multi-agent collaboration has gained increasing attention in the field of autonomous driving. However, as the number of agents grows, the manual annotation required for training collaborative detectors i...
A Generic Competitive-Cooperative Actor-Critic Framework for Deep Reinforcement Learning [0.03%]
一种深度强化学习的通用竞争-合作Actor-Critic框架
Meng Xu,Zihao Wen,Xinhong Chen et al.
Meng Xu et al.
In the field of Deep reinforcement learning (DRL), enhancing exploration capabilities and improving the accuracy of Q-value estimation remain two major challenges. Recently, double-actor DRL methods have emerged as a promising class of DRL ...
Enhancing Adversarial Transferability with Cost-efficient Landscape Flattening [0.03%]
利用成本效益的景观扁平化技术增强对抗样本的迁移性
Zhipeng Wei,Jingjing Chen,Feng Han et al.
Zhipeng Wei et al.
The transferability of adversarial examples across different models has drawn considerable attention recently, particularly in targeted transferability. Prior research has empirically shown that optimizing adversarial perturbations at neigh...
Zheng Wang,Xing Xu,Lei Zhu et al.
Zheng Wang et al.
Eliminating semantic discrepancy between different modalities is the ultimate goal of image text retrieval. However, most of the existing methods only focus on retrieval of the ground-truth instance while ignoring those semantically similar...