Search Results for author: Chenglong Zhao

Found 7 papers, 1 papers with code

Exploring and Utilizing Pattern Imbalance

no code implementations CVPR 2023 Shibin Mei, Chenglong Zhao, Shengchao Yuan, Bingbing Ni

In this paper, we identify pattern imbalance from several aspects, and further develop a new training scheme to avert pattern preference as well as spurious correlation.

Domain Generalization

Energy Attack: On Transferring Adversarial Examples

no code implementations9 Sep 2021 Ruoxi Shi, Borui Yang, Yangzhou Jiang, Chenglong Zhao, Bingbing Ni

Base on the eigenvalues, we can model the energy distribution of adversarial perturbations.

Adversarial Attack

Skeleton2Mesh: Kinematics Prior Injected Unsupervised Human Mesh Recovery

no code implementations ICCV 2021 Zhenbo Yu, Junjie Wang, Jingwei Xu, Bingbing Ni, Chenglong Zhao, Minsi Wang, Wenjun Zhang

The challenges of the latter task are two folds: (1) pose failure (i. e., pose mismatching -- different skeleton definitions in dataset and SMPL , and pose ambiguity -- endpoints have arbitrary joint angle configurations for the same 3D joint coordinates).

3D Pose Estimation Human Mesh Recovery

Learning Black-Box Attackers with Transferable Priors and Query Feedback

1 code implementation NeurIPS 2020 Jiancheng Yang, Yangzhou Jiang, Xiaoyang Huang, Bingbing Ni, Chenglong Zhao

This paper addresses the challenging black-box adversarial attack problem, where only classification confidence of a victim model is available.

Adversarial Attack

Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks

no code implementations6 Aug 2019 Yunxiang Zhang, Chenglong Zhao, Bingbing Ni, Jian Zhang, Haoran Deng

To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and accelerate deep CNNs via channel pruning.

Clustering

Cannot find the paper you are looking for? You can Submit a new open access paper.