1 code implementation • 3 Apr 2024 • Keyu Tian, Yi Jiang, Zehuan Yuan, Bingyue Peng, LiWei Wang
We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction".
Ranked #7 on Image Generation on ImageNet 256x256
1 code implementation • 4 Jan 2024 • Zhaokun Zhou, Kaiwei Che, Wei Fang, Keyu Tian, Yuesheng Zhu, Shuicheng Yan, Yonghong Tian, Li Yuan
To the best of our knowledge, this is the first time that the SNN achieves 80+% accuracy on ImageNet.
1 code implementation • 9 Jan 2023 • Keyu Tian, Yi Jiang, Qishuai Diao, Chen Lin, LiWei Wang, Zehuan Yuan
This is the first use of sparse convolution for 2D masked modeling.
Ranked #1 on Instance Segmentation on COCO 2017 val
no code implementations • NeurIPS 2021 • Keyu Tian, Chen Lin, Ser Nam Lim, Wanli Ouyang, Puneet Dokania, Philip Torr
Automated data augmentation (ADA) techniques have played an important role in boosting the performance of deep models.
1 code implementation • NeurIPS 2020 • Keyu Tian, Chen Lin, Ming Sun, Luping Zhou, Junjie Yan, Wanli Ouyang
On CIFAR-10, we achieve a top-1 error rate of 1. 24%, which is currently the best performing single model without extra training data.
no code implementations • ECCV 2020 • Ronghao Guo, Chen Lin, Chuming Li, Keyu Tian, Ming Sun, Lu Sheng, Junjie Yan
Specifically, the difficulties for architecture searching in such a complex space has been eliminated by the proposed stabilized share-parameter proxy, which employs Stochastic Gradient Langevin Dynamics to enable fast shared parameter sampling, so as to achieve stabilized measurement of architecture performance even in search space with complex topological structures.