Deep residual learning for image steganalysis

421 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

PoTrojan: powerful neural-level trojan designs in deep learning models (2018, background): “Microsoft ResNet [1] achieved an incredible error rate of 3.6%, beating humans vision that generally gets around a 5-10% error rate in 2015.”
Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win (2020, methodology): “Our experiments include the following settings: LeNet5 on MNIST, VGG16 on ImageNet-2012 and ResNet-50 on ImageNet2012.”
Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring (2019, methodology): “The recent success of deep learning for computer vision [21,51] in a number of ﬁelds, such as general image classiﬁcation [109], autonomous transportation systems [57], and medical imaging [63], has driven its application in civil infrastructure inspection and monitoring.”
Chemi-net: a graph convolutional network for accurate drug property prediction (2018, methodology): “This enables the model to obtain feature maps from different convolution levels, which are more straightforward and easier to optimize than only using the reduced feature map 14 : In our experiments, the non-linearity 𝑓 is the Leaky ReLU function with negative slope 𝛼 = 0.01 : For each…”