← Search

Dongdong Hou

2 accepted papers

2019

Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View

CVPR 2019poster

Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically misleading the DNNs. Moreover, adversarial examples can be used to perform an attack on…

Cited by 141PDFScholar
2019

Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation

ICCV 2019accepted

Weakly-supervised learning under image-level labels supervision has been widely applied to semantic segmentation of medical lesions regions. However, 1) most existing models rely on effective constraints to explore the internal representation of lesions, which only produces inaccurate and coarse les…

Cited by 61SourcePDFScholar