no code implementations • ICML 2020 • Yanxi Li, Minjing Dong, Yunhe Wang, Chang Xu
This paper searches for the optimal neural architecture by minimizing a proxy of validation loss.
no code implementations • 16 Mar 2024 • Chengbin Du, Yanxi Li, Chang Xu
VMamba exhibits exceptional generalizability with out-of-distribution data but shows scalability weaknesses against natural adversarial examples and common corruptions.
1 code implementation • 16 Jul 2023 • Xiaohuan Pei, Yanxi Li, Minjing Dong, Chang Xu
With the increasing number of new neural architecture designs and substantial existing neural architectures, it becomes difficult for the researchers to situate their contributions compared with existing neural architectures or establish the connections between their designs and other relevant ones.
no code implementations • 7 Jun 2023 • Xiaohuan Pei, Yanxi Li, Chang Xu
In the one-shot tuning phase, we sample a data from the support set as part of the prompt for GPT to generate a textual summary, which is then used to recover the original data.
1 code implementation • NeurIPS 2023 • Chengbin Du, Yanxi Li, Zhongwei Qiu, Chang Xu
Recently, text-to-image models have been thriving.
no code implementations • CVPR 2023 • Yanxi Li, Chang Xu
Although deep neural networks (DNNs) have shown great successes in computer vision tasks, they are vulnerable to perturbations on inputs, and there exists a trade-off between the natural accuracy and robustness to such perturbations, which is mainly caused by the existence of robust non-predictive features and non-robust predictive features.
1 code implementation • International Conference on Machine Learning 2022 • Yanxi Li, Xinghao Chen, Minjing Dong, Yehui Tang, Yunhe Wang, Chang Xu
Recently, neural architectures with all Multi-layer Perceptrons (MLPs) have attracted great research interest from the computer vision community.
Ranked #492 on Image Classification on ImageNet
10 code implementations • CVPR 2022 • Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu, Yanxi Li, Chao Xu, Yunhe Wang
To dynamically aggregate tokens, we propose to represent each token as a wave function with two parts, amplitude and phase.
no code implementations • NeurIPS 2021 • Yanxi Li, Zhaohui Yang, Yunhe Wang, Chang Xu
With the tremendous advances in the architecture and scale of convolutional neural networks (CNNs) over the past few decades, they can easily reach or even exceed the performance of humans in certain tasks.
1 code implementation • CVPR 2021 • Xiu Su, Tao Huang, Yanxi Li, Shan You, Fei Wang, Chen Qian, ChangShui Zhang, Chang Xu
One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network, which only needs to be trained once.
1 code implementation • NeurIPS 2020 • Yanxi Li, Zhaohui Yang, Yunhe Wang, Chang Xu
The power of deep neural networks is to be unleashed for analyzing a large volume of data (e. g. ImageNet), but the architecture search is often executed on another smaller dataset (e. g. CIFAR-10) to finish it in a feasible time.
no code implementations • 2 Sep 2020 • Minjing Dong, Yanxi Li, Yunhe Wang, Chang Xu
We explore the relationship among adversarial robustness, Lipschitz constant, and architecture parameters and show that an appropriate constraint on architecture parameters could reduce the Lipschitz constant to further improve the robustness.