Shilong Bao,Qianqian Xu,Zhiyong Yang et al.
Shilong Bao et al.
The current studies of provable robustness for deep neural networks (DNNs) usually assume that the class distribution is overall balanced. However, in real-world applications especially for safety-sensitive systems, the class distribution o...
Replay Without Saving: Prototype Derivation and Distribution Rebalance for Class-Incremental Semantic Segmentation [0.03%]
无需保存的回放：面向类增量语义分割的原型演绎与分布重平衡方法
Jinpeng Chen,Runmin Cong,Yuxuan Luo et al.
Jinpeng Chen et al.
The research of class-incremental semantic segmentation (CISS) seeks to enhance semantic segmentation methods by enabling the progressive learning of new classes while preserving knowledge of previously learned ones. A significant yet often...
Yongkun Du,Zhineng Chen,Caiyan Jia et al.
Yongkun Du et al.
Scene text recognition (STR) methods have struggled to attain high accuracy and fast inference speed. Auto-Regressive (AR)-based models implement the recognition in a character-by-character manner, showing superiority in accuracy but with s...
Duo Peng,Qiuhong Ke,Mark He Huang et al.
Duo Peng et al.
Text-to-Image (T2I) models have advanced significantly, but their growing popularity raises security concerns due to their potential to generate harmful images. To address these issues, we propose UPAM, a novel framework to evaluate the rob...
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting [0.03%]
面向表达的谱-时序图神经网络在时间序列预测中的应用研究
Ming Jin,Guangsi Shi,Yuan-Fang Li et al.
Ming Jin et al.
Time series forecasting has remained a focal point due to its vital applications in sectors such as energy management and transportation planning. Spectral-temporal graph neural network is a promising abstraction underlying most time series...
Yong Li,Yufei Sun,Zhen Cui et al.
Yong Li et al.
The fairness of face recognition (FR) is a challenging issue to numerous FR algorithms in the modern pluralistic and egalitarian society. In this work, we propose an instance-consistent fair face recognition (IC-FFR) method by fulfilling co...
A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurring [0.03%]
广义空间降质下基于张量的高光谱图像超分辨率通用模型
Yinjian Wang,Wei Li,Yuanyuan Gui et al.
Yinjian Wang et al.
Hyperspectral super-resolution is commonly accomplished by the fusing of a hyperspectral imaging of low spatial resolution with a multispectral image of high spatial resolution, and many tensor-based approaches to this task have been recent...
Xingyu Xie,Zhijie Lin,Kim-Chuan Toh et al.
Xingyu Xie et al.
To efficiently train large-scale models, low-bit gradient communication compresses full-precision gradients on local GPU nodes into low-precision ones for higher gradient synchronization efficiency among GPU nodes. However, it often degrade...
Jinli Yao,Jie Pan,Yong Zeng
Jinli Yao
The development of a nonparametric and versatile clustering algorithm has been a longstanding challenge in unsupervised learning due to the exploratory nature of the clustering problem. This study presents a novel algorithm, named Gauging-,...
Haoyue Liu,Jinghan Xu,Shihan Peng et al.
Haoyue Liu et al.
We focus on a very challenging task: imaging at nighttime dynamic scenes. Conventional RGB cameras struggle with the trade-off between long exposure for low-light imaging and short exposure for capturing dynamic scenes. Event cameras react ...