Detecting camouflaged object in frequency domain
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 …
their environment, which has various downstream applications in fields such as medicine …
Federated learning with label distribution skew via logits calibration
Traditional federated optimization methods perform poorly with heterogeneous data (ie,
accuracy reduction), especially for highly skewed data. In this paper, we investigate the label …
accuracy reduction), especially for highly skewed data. In this paper, we investigate the label …
Segment, magnify and reiterate: Detecting camouflaged objects the hard way
It is challenging to accurately detect camouflaged objects from their highly similar
surroundings. Existing methods mainly leverage a single-stage detection fashion, while …
surroundings. Existing methods mainly leverage a single-stage detection fashion, while …
Shape matters: deformable patch attack
Though deep neural networks (DNNs) have demonstrated excellent performance in
computer vision, they are susceptible and vulnerable to carefully crafted adversarial …
computer vision, they are susceptible and vulnerable to carefully crafted adversarial …
Highly accurate dichotomous image segmentation
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 …
which aims to segment highly accurate objects from natural images. To this end, we …
Towards practical certifiable patch defense with vision transformer
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 …
can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous …
Towards efficient data free black-box adversarial attack
Classic black-box adversarial attacks can take advantage of transferable adversarial
examples generated by a similar substitute model to successfully fool the target model …
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 …
underwater environment, such as light attenuation, scattering, water turbidity, and the …