Detecting camouflaged object in frequency domain

Y Zhong, B Li, L Tang, S Kuang… - Proceedings of the …, 2022 - openaccess.thecvf.com
Camouflaged object detection (COD) aims to identify objects that are perfectly embedded in
their environment, which has various downstream applications in fields such as medicine …

Federated learning with label distribution skew via logits calibration

J Zhang, Z Li, B Li, J Xu, S Wu… - … on Machine Learning, 2022 - proceedings.mlr.press
Traditional federated optimization methods perform poorly with heterogeneous data (ie,
accuracy reduction), especially for highly skewed data. In this paper, we investigate the label …

Segment, magnify and reiterate: Detecting camouflaged objects the hard way

Q Jia, S Yao, Y Liu, X Fan, R Liu… - Proceedings of the …, 2022 - openaccess.thecvf.com
It is challenging to accurately detect camouflaged objects from their highly similar
surroundings. Existing methods mainly leverage a single-stage detection fashion, while …

Shape matters: deformable patch attack

Z Chen, B Li, S Wu, J Xu, S Ding, W Zhang - European conference on …, 2022 - Springer
Though deep neural networks (DNNs) have demonstrated excellent performance in
computer vision, they are susceptible and vulnerable to carefully crafted adversarial …

Highly accurate dichotomous image segmentation

X Qin, H Dai, X Hu, DP Fan, L Shao… - European Conference on …, 2022 - Springer
We present a systematic study on a new task called dichotomous image segmentation (DIS),
which aims to segment highly accurate objects from natural images. To this end, we …

Towards practical certifiable patch defense with vision transformer

Z Chen, B Li, J Xu, S Wu, S Ding… - Proceedings of the …, 2022 - openaccess.thecvf.com
Patch attacks, one of the most threatening forms of physical attack in adversarial examples,
can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous …

Towards efficient data free black-box adversarial attack

J Zhang, B Li, J Xu, S Wu, S Ding… - Proceedings of the …, 2022 - openaccess.thecvf.com
Classic black-box adversarial attacks can take advantage of transferable adversarial
examples generated by a similar substitute model to successfully fool the target model …

Underwater Detection: A Brief Survey and A New Multitask Dataset

Y Wei, Y Wang, B Zhu, C Lin, D Wu, X Xue… - International Journal of …, 2024 - sciltp.com
Underwater detection poses significant challenges due to the unique characteristics of the
underwater environment, such as light attenuation, scattering, water turbidity, and the …