Search Results for author: Chong Fu

Found 16 papers, 4 papers with code

PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation

no code implementations28 Feb 2024 Haoyu Xie, Changqi Wang, Jian Zhao, Yang Liu, Jun Dan, Chong Fu, Baigui Sun

To address this issue, we propose a robust contrastive-based S4 framework, termed the Probabilistic Representation Contrastive Learning (PRCL) framework to enhance the robustness of the unsupervised training process.

Contrastive Learning Semi-Supervised Semantic Segmentation

Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation

no code implementations ICCV 2023 Changqi Wang, Haoyu Xie, Yuhui Yuan, Chong Fu, Xiangyu Yue

To improve the robustness of representations, powerful methods introduce a pixel-wise contrastive learning approach in latent space (i. e., representation space) that aggregates the representations to their prototypes in a fully supervised manner.

Contrastive Learning Semi-Supervised Semantic Segmentation

Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation

no code implementations CVPR 2023 Xu Zheng, Jinjing Zhu, Yexin Liu, Zidong Cao, Chong Fu, Lin Wang

Moreover, adversarial intra-projection training is proposed to reduce the inherent gap, between the features of the pinhole images and those of the ERP and TP images, respectively.

Scene Understanding Semantic Segmentation +1

FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases

1 code implementation28 Feb 2023 Chong Fu, Xuhong Zhang, Shouling Ji, Ting Wang, Peng Lin, Yanghe Feng, Jianwei Yin

Thus, in this paper, we propose FreeEagle, the first data-free backdoor detection method that can effectively detect complex backdoor attacks on deep neural networks, without relying on the access to any clean samples or samples with the trigger.

Backdoor Attack

Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations

1 code implementation26 Oct 2022 Haoyu Xie, Changqi Wang, Mingkai Zheng, Minjing Dong, Shan You, Chong Fu, Chang Xu

In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the latent space.

Contrastive Learning Semi-Supervised Semantic Segmentation

Label Inference Attacks Against Vertical Federated Learning

2 code implementations USENIX Security 22 2022 Chong Fu, Xuhong Zhang, Shouling Ji, Jinyin Chen, Jingzheng Wu, Shanqing Guo, Jun Zhou, Alex X. Liu, Ting Wang

However, we discover that the bottom model structure and the gradient update mechanism of VFL can be exploited by a malicious participant to gain the power to infer the privately owned labels.

Vertical Federated Learning

Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students

no code implementations6 Sep 2022 Xu Zheng, Yunhao Luo, Chong Fu, Kangcheng Liu, Lin Wang

To this end, we propose class-aware feature consistency distillation (CFCD) that first leverages the outputs of each student as the pseudo labels and generates class-aware feature (CF) maps for knowledge transfer between the two students.

Semi-Supervised Semantic Segmentation Transfer Learning

Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settings

no code implementations7 Apr 2022 Yuhao Mao, Chong Fu, Saizhuo Wang, Shouling Ji, Xuhong Zhang, Zhenguang Liu, Jun Zhou, Alex X. Liu, Raheem Beyah, Ting Wang

To bridge this critical gap, we conduct the first large-scale systematic empirical study of transfer attacks against major cloud-based MLaaS platforms, taking the components of a real transfer attack into account.

CatchBackdoor: Backdoor Testing by Critical Trojan Neural Path Identification via Differential Fuzzing

no code implementations24 Dec 2021 Haibo Jin, Ruoxi Chen, Jinyin Chen, Yao Cheng, Chong Fu, Ting Wang, Yue Yu, Zhaoyan Ming

Existing DNN testing methods are mainly designed to find incorrect corner case behaviors in adversarial settings but fail to discover the backdoors crafted by strong trojan attacks.

DNN Testing

Uncertainty-Aware Deep Co-training for Semi-supervised Medical Image Segmentation

no code implementations23 Nov 2021 Xu Zheng, Chong Fu, Haoyu Xie, Jialei Chen, Xingwei Wang, Chiu-Wing Sham

However, due to the scarcity of labeled data, the features extracted by the models are limited in supervised learning, and the quality of predictions for unlabeled data also cannot be guaranteed.

Image Segmentation Semantic Segmentation +1

A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning

no code implementations28 Jun 2021 Wenchao Zhang, Chong Fu, Xiangshi Chang, Tengfei Zhao, Xiang Li, Chiu-Wing Sham

Without losing generality, we can also build a more lighter head network for other multi-stage detectors by assembling our method.

object-detection Object Detection +1

Dense Global Context Aware RCNN for Object Detection

no code implementations1 Jan 2021 Wenchao Zhang, Haoyu Xie, Mai Zhu, Chong Fu

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map.

Object object-detection +1

Global Context Aware RCNN for Object Detection

no code implementations4 Dec 2020 Wenchao Zhang, Chong Fu, Haoyu Xie, Mai Zhu, Ming Tie, Junxin Chen

The core component of our GCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement, respectively.

Object object-detection +1

Convolutional Neural Networks combined with Runge-Kutta Methods

1 code implementation ICLR 2019 Mai Zhu, Bo Chang, Chong Fu

A convolutional neural network can be constructed using numerical methods for solving dynamical systems, since the forward pass of the network can be regarded as a trajectory of a dynamical system.

Image Classification

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