Correlation-based structural dropout for convolutional neural networks

TL;DR: Zhang et al. as mentioned in this paper proposed an effective Deep Image Prior Driven Defense (DIPDefend) method against adversarial examples with a DIP generator to fit the target/adversarial input.

TL;DR: Wang et al. as mentioned in this paper proposed a novel water level measurement method based on deep learning (YOLOv5s, convolutional neural network) to overcome poor scene adaptability and weak robustness.

TL;DR: This paper proposes a DomainDrop framework to continuously enhance the channel robustness to domain shifts, where a domain discriminator is used to identify and drop unstable channels in feature maps of each network layer during forward propagation.

TL;DR: In this article , a novel near infrared (NIR) application for determination of alcohols-diesel is presented using the strategy of combining NIR spectroscopy with gramian angular field (GAF) image coding and deep convolution neural network (CNN).

TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.