no code implementations • ECCV 2020 • Yanchun Xie, Jimin Xiao, Ming-Jie Sun, Chao Yao, Kai-Zhu Huang
To this end, we engaged neural texture transfer to swap texture features between the low-resolution image and the high-resolution reference image.
4 code implementations • NeurIPS 2020 • Hadi Salman, Ming-Jie Sun, Greg Yang, Ashish Kapoor, J. Zico Kolter
We present a method for provably defending any pretrained image classifier against $\ell_p$ adversarial attacks.
1 code implementation • 19 Nov 2019 • Bingfeng Zhang, Jimin Xiao, Yunchao Wei, Ming-Jie Sun, Kai-Zhu Huang
Such reliable regions are then directly served as ground-truth labels for the parallel segmentation branch, where a newly designed dense energy loss function is adopted for optimization.
Ranked #22 on Semantic Segmentation on PASCAL VOC 2012 val
1 code implementation • 2 Nov 2019 • Hui Li, Jimin Xiao, Ming-Jie Sun, Eng Gee Lim, Yao Zhao
To tackle this problem, we propose to iteratively guess pseudo labels for the unlabeled image samples, which are later used to update the re-identification model together with the labelled samples.
2 code implementations • ICLR 2019 • Zhuang Liu, Ming-Jie Sun, Tinghui Zhou, Gao Huang, Trevor Darrell
Our observations are consistent for multiple network architectures, datasets, and tasks, which imply that: 1) training a large, over-parameterized model is often not necessary to obtain an efficient final model, 2) learned "important" weights of the large model are typically not useful for the small pruned model, 3) the pruned architecture itself, rather than a set of inherited "important" weights, is more crucial to the efficiency in the final model, which suggests that in some cases pruning can be useful as an architecture search paradigm.
no code implementations • 27 Jul 2016 • David B. Phillips, Ming-Jie Sun, Jonathan M. Taylor, Matthew P. Edgar, Stephen M. Barnett, Graham G. Gibson, Miles J. Padgett
To mitigate this, a range of compressive sensing techniques have been developed which rely on a priori knowledge of the scene to reconstruct images from an under-sampled set of measurements.