63 citations · 94 across the 9 of their papers we have counts for
9 papers
Task-Robust Pre-Training for Worst-Case Downstream Adaptation
Jianghui Wang, Yang Chen, Xingyu Xie +2
Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior…
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
Xingyu Xie, Pan Zhou, Huan Li +2
In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To r…
Global Convergence of Over-parameterized Deep Equilibrium Models
Zenan Ling, Xingyu Xie, Qiuhao Wang +2
A deep equilibrium model (DEQ) is implicitly defined through an equilibrium point of an infinite-depth weight-tied model with an input-injection. Instead of infinite computations,…
High Quality Segmentation for Ultra High-resolution Images
Tiancheng Shen, Yuechen Zhang, Lu Qi +5
To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation. Common strategies, such as down-sampling, patch cropping, and cascade…
Optimization Induced Equilibrium Networks
Xingyu Xie, Qiuhao Wang, Zenan Ling +4
Implicit equilibrium models, i.e., deep neural networks (DNNs) defined by implicit equations, have been becoming more and more attractive recently. In this paper, we investigate an…
Maximum-and-Concatenation Networks
Xingyu Xie, Hao Kong, Jianlong Wu +3
While successful in many fields, deep neural networks (DNNs) still suffer from some open problems such as bad local minima and unsatisfactory generalization performance. In this wo…
Differentiable Linearized ADMM
Xingyu Xie, Jianlong Wu, Zhisheng Zhong +2
Recently, a number of learning-based optimization methods that combine data-driven architectures with the classical optimization algorithms have been proposed and explored, showing…
Matrix Recovery with Implicitly Low-Rank Data
Xingyu Xie, Jianlong Wu, Guangcan Liu +1
In this paper, we study the problem of matrix recovery, which aims to restore a target matrix of authentic samples from grossly corrupted observations. Most of the existing methods…
Surface Reconstruction with Data-driven Exemplar Priors
Oussama Remil, Qian Xie, Xingyu Xie +2
In this paper, we propose a framework to reconstruct 3D models from raw scanned points by learning the prior knowledge of a specific class of objects. Unlike previous work that heu…