no code implementations • 27 Nov 2023 • Chenglin Yang, Siyuan Qiao, Yuan Cao, Yu Zhang, Tao Zhu, Alan Yuille, Jiahui Yu
To tackle this problem, we redesign the scoring objective for the captioner to alleviate the distributional bias and focus on measuring the gain of information brought by the visual inputs.
2 code implementations • 4 Oct 2022 • Chenglin Yang, Siyuan Qiao, Qihang Yu, Xiaoding Yuan, Yukun Zhu, Alan Yuille, Hartwig Adam, Liang-Chieh Chen
The tiny-MOAT family is also benchmarked on downstream tasks, serving as a baseline for the community.
Ranked #1 on Object Detection on MS COCO
1 code implementation • CVPR 2022 • Chenglin Yang, Yilin Wang, Jianming Zhang, He Zhang, Zijun Wei, Zhe Lin, Alan Yuille
We propose Lite Vision Transformer (LVT), a novel light-weight transformer network with two enhanced self-attention mechanisms to improve the model performances for mobile deployment.
3 code implementations • 12 Jul 2021 • Chenglin Yang, Siyuan Qiao, Adam Kortylewski, Alan Yuille
Self-Attention has become prevalent in computer vision models.
1 code implementation • 13 Dec 2020 • Chenglin Yang, Yilin Wang, Jianming Zhang, He Zhang, Zhe Lin, Alan Yuille
To evaluate segmentation quality near object boundaries, we propose the Meticulosity Quality (MQ) score considering both the mask coverage and boundary precision.
no code implementations • 1 Dec 2020 • Christian Cosgrove, Adam Kortylewski, Chenglin Yang, Alan Yuille
Second, we find that compositional deep networks, which have part-based representations that lead to innate robustness to natural occlusion, are robust to patch attacks on PASCAL3D+ and the German Traffic Sign Recognition Benchmark, without adversarial training.
2 code implementations • ECCV 2020 • Chenglin Yang, Adam Kortylewski, Cihang Xie, Yinzhi Cao, Alan Yuille
PatchAttack induces misclassifications by superimposing small textured patches on the input image.
no code implementations • CVPR 2019 • Chenglin Yang, Lingxi Xie, Chi Su, Alan L. Yuille
Optimizing a deep neural network is a fundamental task in computer vision, yet direct training methods often suffer from over-fitting.
no code implementations • 15 May 2018 • Chenglin Yang, Lingxi Xie, Siyuan Qiao, Alan Yuille
We focus on the problem of training a deep neural network in generations.