Haolin Pan,Yong Guo,Mianjie Yu et al.
Haolin Pan et al.
Real-world data often follows a long-tailed distribution, where a few head classes occupy most of the data and a large number of tail classes only contain very limited samples. In practice, deep models often show poor generalization perform...
OTAMatch: Optimal Transport Assignment with PseudoNCE for Semi-supervised Learning [0.03%]
基于伪噪声对比估计的最优传输分配半监督学习方法
Jinjin Zhang,Junjie Liu,Debang Li et al.
Jinjin Zhang et al.
In semi-supervised learning (SSL), many approaches follow the effective self-training paradigm with consistency regularization, utilizing threshold heuristics to alleviate label noise. However, such threshold heuristics lead to the underuti...
Duo Peng,Qiuhong Ke,ArulMurugan Ambikapathi et al.
Duo Peng et al.
Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain. Inspired by diffusion models which have strong capability to gradually convert data distrib...
HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation [0.03%]
HAFormer：利用层次感知特征进行轻量级语义分割
Guoan Xu,Wenjing Jia,Tao Wu et al.
Guoan Xu et al.
Both Convolutional Neural Networks (CNNs) and Transformers have shown great success in semantic segmentation tasks. Efforts have been made to integrate CNNs with Transformer models to capture both local and global context interactions. Howe...
Yunzhong Hou,Stephen Gould,Liang Zheng
Yunzhong Hou
Color quantization reduces the number of colors used in an image while preserving its content, which is essential in pixel art and knitting art creation. Traditional methods primarily focus on visual fidelity and treat it as a clustering pr...
Cayley Rotation Averaging: Multiple Camera Averaging Under the Cayley Framework [0.03%]
基于凯莱框架的相机旋转平均算法
Qiulei Dong,Shuang Deng,Yuzhen Liu
Qiulei Dong
Rotation averaging, which aims to calculate the absolute rotations of a set of cameras from a redundant set of their relative rotations, is an important and challenging topic arising in the study of structure from motion. A central problem ...
Tai-Jiang Mu,Ming-Yuan Shen,Yu-Kun Lai et al.
Tai-Jiang Mu et al.
2D-3D joint learning is essential and effective for fundamental 3D vision tasks, such as 3D semantic segmentation, due to the complementary information these two visual modalities contain. Most current 3D scene semantic segmentation methods...
Jie Chen,Yingke Chen,Zhu Wang et al.
Jie Chen et al.
Incomplete multiview clustering (IMVC) aims to reveal the underlying structure of incomplete multiview data by partitioning data samples into clusters. Several graph-based methods exhibit a strong ability to explore high-order information a...
Enhancing Low-Light Light Field Images With a Deep Compensation Unfolding Network [0.03%]
基于深度补偿网络的低光场景计算全聚焦方法研究
Xianqiang Lyu,Junhui Hou
Xianqiang Lyu
This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured under low-light conditions. DCUNet is designed with a multi...
Jiwei Chen,Zengfu Wang
Jiwei Chen
Due to different installation angles, heights, and positions of the camera installation in real-world scenes, it is difficult for crowd counting models to work in unseen surveillance scenes. In this paper, we are interested in accurate crow...