Like Human Rethinking: Contour Transformer AutoRegression for Referring Remote Sensing Interpretation [0.03%]
如人再思：轮廓变压器自回归在遥感解译中的应用
Jinming Chai,Licheng Jiao,Xiaoqiang Lu et al.
Jinming Chai et al.
Referring remote sensing interpretation holds significant application value in various scenarios such as ecological protection, resource exploration, and emergency management. However, referring remote sensing expression comprehension and s...
Semantic Contrast for Domain-Robust Underwater Image Quality Assessment [0.03%]
基于语义对比的鲁棒域水下图像质量评估方法
Jingchun Zhou,Chunjiang Liu,Qiuping Jiang et al.
Jingchun Zhou et al.
Underwater image quality assessment (UIQA) is hindered by complex degradation and domain shifts across aquatic environments. Existing no-reference IQA methods rely on costly and subjective mean opinion scores (MOS), which limit their genera...
Towards Enhanced Representation Learning for Single-Source Domain Generalization in LiDAR Semantic Segmentation [0.03%]
面向单源域泛化的LiDAR语义分割的增强表示学习方法研究
Hyeonseong Kim,Yoonsu Kang,Changgyoon Oh et al.
Hyeonseong Kim et al.
With the success of the 3D deep learning models, various perception technologies for autonomous driving have been developed in the LiDAR domain. While these models perform well in the trained source domain, they struggle in unseen domains w...
Zheng Zhang,Peng Zhou,Aiting Yao et al.
Zheng Zhang et al.
Subspace clustering is one of the most popular clustering methods due to its effectiveness. Although subspace clustering methods have been demonstrated to achieve promising performance, they still lack interpretability, especially when hand...
Hongbo Zhao,Fei Zhu,Bolin Ni et al.
Hongbo Zhao et al.
For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests originate at any time from both users and model owners, and the...
DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation [0.03%]
DyDiT++：具有时间和空间动态的扩散变压器，用于高效的视觉生成
Wangbo Zhao,Yizeng Han,Jiasheng Tang et al.
Wangbo Zhao et al.
Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior perfor mance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the stat...
BlindU: Blind Machine Unlearning without Revealing Erasing Data [0.03%]
盲机器卸载学习方法 BlindU：无需擦除数据的盲机器卸载学习
Weiqi Wang,Zhiyi Tian,Chenhan Zhang et al.
Weiqi Wang et al.
Machine unlearning enables data holders to remove the contribution of their specified samples from trained models to protect their privacy. However, it is paradoxical that most unlearning methods require the unlearning requesters to firstly...
Single-Photon Imaging in Complex Scenarios via Physics-Informed Deep Neural Networks [0.03%]
基于物理信息的深度神经网络在复杂场景中的单光子成像
Siao Cai,Zhicheng Yu,Shaobing Gao et al.
Siao Cai et al.
Single-photon imaging uses single-photon-sensitive picosecond-resolution sensors to capture 3D structure and supports diverse applications, but success remains mostly limited to simple scenes. In complex scenarios, traditional methods degra...
Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attention [0.03%]
通过图Sinkhorn注意力改进子图提取以进行图不变量学习
Junchi Yan,Fangyu Ding,Jiawei Sun et al.
Junchi Yan et al.
Graph invariant learning (GIL) seeks invariant relations between graphs and labels under distribution shifts. Recent works try to extract an invariant subgraph to improve out-of-distribution (OOD) generalization, yet existing approaches eit...
Consistency-Aware Spot-Guided Transformer for Accurate and Versatile Point Cloud Registration [0.03%]
一种一致性和兴趣点感知的变压器网络框架用于准确且通用的点云配准问题研究
Renlang Huang,Li Chai,Yufan Tang et al.
Renlang Huang et al.
Deep learning-based feature matching has showcased great superiority for point cloud registration. While coarse-to-fine matching architectures are prevalent, they typically perform sparse and geometrically inconsistent coarse matching. This...