4 papers
One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting?
Ziang Li, Yue Huang, Guoxu Zhou +4
Patch-based autoregressive time-series forecasting often ties input representation, learned transitions, and recursive execution to one patch length. We ask which of these roles ca…
Single Image Reflection Separation via Dual Prior Interaction Transformer
Yue Huang, Tianle Hu, Yu Chen +3
Single image reflection separation aims to separate the transmission and reflection layers from a mixed image. Existing methods typically combine general priors from pre-trained mo…
A Theoretical View of Linear Backpropagation and Its Convergence
Ziang Li, Yiwen Guo, Haodi Liu +1
Backpropagation (BP) is widely used for calculating gradients in deep neural networks (DNNs). Applied often along with stochastic gradient descent (SGD) or its variants, BP is cons…
Learned ISTA with Error-based Thresholding for Adaptive Sparse Coding
Ziang Li, Kailun Wu, Yiwen Guo +1
Drawing on theoretical insights, we advocate an error-based thresholding (EBT) mechanism for learned ISTA (LISTA), which utilizes a function of the layer-wise reconstruction error…