Rapid advancement in Machine Learning (ML) and Artificial Intelligence (AI) has brought increased attention to AI technologies’ potential vulnerability and reliability. This paper identifies the ...threat of the network incorrectly relying on the latent features that can stay undetectable during validation but cause severe issues in life applications and thus susceptible to adversarial attacks. Furthermore, we propose a semi-automated method to identify this hazard, relying on the Gradual Extrapolation technique to sharpen saliency maps. The method combines well-known techniques: object detection tools and saliency map obtaining formula joined with an enhancement to highlight the vital object, not the area. The proposed method introduces a new metric, the ”Discriminating Feature Ratio” (DFR), to assess the extent to which a model learns only a fraction of an object, such as a specific feature instead of the whole object. By detecting classes with outlying DFRs, the method highlights potential cases where the model’s understanding is limited to certain features, prompting further scrutiny and improved model reliability. The study on ImageNet trained models demonstrates the effectiveness of the DFR in identifying problematic classes and potential vulnerabilities even in state of the art networks. Overall, the introduced method provides valuable insights into deep neural network decision-making processes, uncovering classes with spurious or latent feature reliance issues and potential vulnerabilities. It can serve as simple validation mechanism, similar to accuracy, precision, and recall for a large-scale datasets trained models. By enhancing the transparency and interpretability of deep learning models, this research contributes to improving the robustness and reliability of CNNs in real-world applications. Datasets and code are available publicly on GitHub: https://github.com/szandala/Latent-Features-Detection
Display omitted
•Addresses CNNs’ vulnerability to latent features, impacting real-life applications.•Proposed method combines object detection and sharpened saliency map techniques.•Experiments reveal state-of-the-art models’ susceptibility to latent feature focus.•Method identifies problematic classes enabling successful adversarial attacks.•Despite limitations, the method offers insights into CNNs’ decision-making at scale.
Scene text detection is an important step of scene text recognition system and also a challenging problem. Different from general object detections, the main challenges of scene text detection lie on ...arbitrary orientations, small sizes, and significantly variant aspect ratios of text in natural images. In this paper, we present an end-to-end trainable fast scene text detector, named TextBoxes++, which detects arbitrary-oriented scene text with both high accuracy and efficiency in a single network forward pass. No post-processing other than efficient non-maximum suppression is involved. We have evaluated the proposed TextBoxes++ on four public data sets. In all experiments, TextBoxes++ outperforms competing methods in terms of text localization accuracy and runtime. More specifically, TextBoxes++ achieves an f-measure of 0.817 at 11.6 frames/s for 1024 × 1024 ICDAR 2015 incidental text images and an f-measure of 0.5591 at 19.8 frames/s for 768 × 768 COCO-Text images. Furthermore, combined with a text recognizer, TextBoxes++ significantly outperforms the state-of-the-art approaches for word spotting and end-to-end text recognition tasks on popular benchmarks. Code is available at: https://github.com/MhLiao/TextBoxes_plusplus.
Convolution in Convolution for Network in Network Pang, Yanwei; Sun, Manli; Jiang, Xiaoheng ...
IEEE transaction on neural networks and learning systems,
05/2018, Volume:
29, Issue:
5
Journal Article
Open access
Network in network (NiN) is an effective instance and an important extension of deep convolutional neural network consisting of alternating convolutional layers and pooling layers. Instead of using a ...linear filter for convolution, NiN utilizes shallow multilayer perceptron (MLP), a nonlinear function, to replace the linear filter. Because of the powerfulness of MLP and 1 × 1 convolutions in spatial domain, NiN has stronger ability of feature representation and hence results in better recognition performance. However, MLP itself consists of fully connected layers that give rise to a large number of parameters. In this paper, we propose to replace dense shallow MLP with sparse shallow MLP. One or more layers of the sparse shallow MLP are sparely connected in the channel dimension or channel-spatial domain. The proposed method is implemented by applying unshared convolution across the channel dimension and applying shared convolution across the spatial dimension in some computational layers. The proposed method is called convolution in convolution (CiC). The experimental results on the CIFAR10 data set, augmented CIFAR10 data set, and CIFAR100 data set demonstrate the effectiveness of the proposed CiC method.
The success of convolutional neural networks (CNNs) in computer vision applications has been accompanied by a significant increase of computation and memory costs, which prohibits their usage on ...resource-limited environments, such as mobile systems or embedded devices. To this end, the research of CNN compression has recently become emerging. In this paper, we propose a novel filter pruning scheme, termed structured sparsity regularization (SSR), to simultaneously speed up the computation and reduce the memory overhead of CNNs, which can be well supported by various off-the-shelf deep learning libraries. Concretely, the proposed scheme incorporates two different regularizers of structured sparsity into the original objective function of filter pruning, which fully coordinates the global output and local pruning operations to adaptively prune filters. We further propose an alternative updating with Lagrange multipliers (AULM) scheme to efficiently solve its optimization. AULM follows the principle of alternating direction method of multipliers (ADMM) and alternates between promoting the structured sparsity of CNNs and optimizing the recognition loss, which leads to a very efficient solver (<inline-formula> <tex-math notation="LaTeX">2.5\times </tex-math></inline-formula> to the most recent work that directly solves the group sparsity-based regularization). Moreover, by imposing the structured sparsity, the online inference is extremely memory-light since the number of filters and the output feature maps are simultaneously reduced. The proposed scheme has been deployed to a variety of state-of-the-art CNN structures, including LeNet, AlexNet, VGGNet, ResNet, and GoogLeNet, over different data sets. Quantitative results demonstrate that the proposed scheme achieves superior performance over the state-of-the-art methods. We further demonstrate the proposed compression scheme for the task of transfer learning, including domain adaptation and object detection, which also show exciting performance gains over the state-of-the-art filter pruning methods.
Understanding deep convolutional networks Mallat, Stéphane
Philosophical transactions - Royal Society. Mathematical, Physical and engineering sciences/Philosophical transactions - Royal Society. Mathematical, physical and engineering sciences,
04/2016, Volume:
374, Issue:
2065
Journal Article
Peer reviewed
Open access
Deep convolutional networks provide state-of-the-art classifications and regressions results over many high-dimensional problems. We review their architecture, which scatters data with a cascade of ...linear filter weights and nonlinearities. A mathematical framework is introduced to analyse their properties. Computations of invariants involve multiscale contractions with wavelets, the linearization of hierarchical symmetries and sparse separations. Applications are discussed.
Deep learning methods, and in particular convolutional neural networks (CNNs), have led to an enormous breakthrough in a wide range of computer vision tasks, primarily by using large-scale annotated ...datasets. However, obtaining such datasets in the medical domain remains a challenge. In this paper, we present methods for generating synthetic medical images using recently presented deep learning Generative Adversarial Networks (GANs). Furthermore, we show that generated medical images can be used for synthetic data augmentation, and improve the performance of CNN for medical image classification. Our novel method is demonstrated on a limited dataset of computed tomography (CT) images of 182 liver lesions (53 cysts, 64 metastases and 65 hemangiomas). We first exploit GAN architectures for synthesizing high quality liver lesion ROIs. Then we present a novel scheme for liver lesion classification using CNN. Finally, we train the CNN using classic data augmentation and our synthetic data augmentation and compare performance. In addition, we explore the quality of our synthesized examples using visualization and expert assessment. The classification performance using only classic data augmentation yielded 78.6% sensitivity and 88.4% specificity. By adding the synthetic data augmentation the results increased to 85.7% sensitivity and 92.4% specificity. We believe that this approach to synthetic data augmentation can generalize to other medical classification applications and thus support radiologists’ efforts to improve diagnosis.
The emergence of Coronavirus Disease 2019 (COVID-19) in early December 2019 has caused immense damage to health and global well-being. Currently, there are approximately five million confirmed cases ...and the novel virus is still spreading rapidly all over the world. Many hospitals across the globe are not yet equipped with an adequate amount of testing kits and the manual Reverse Transcription-Polymerase Chain Reaction (RT-PCR) test is time-consuming and troublesome. It is hence very important to design an automated and early diagnosis system which can provide fast decision and greatly reduce the diagnosis error. The chest X-ray images along with emerging Artificial Intelligence (AI) methodologies, in particular Deep Learning (DL) algorithms have recently become a worthy choice for early COVID-19 screening. This paper proposes a DL assisted automated method using X-ray images for early diagnosis of COVID-19 infection. We evaluate the effectiveness of eight pre-trained Convolutional Neural Network (CNN) models such as AlexNet, VGG-16, GoogleNet, MobileNet-V2, SqueezeNet, ResNet-34, ResNet-50 and Inception-V3 for classification of COVID-19 from normal cases. Also, comparative analyses have been made among these models by considering several important factors such as batch size, learning rate, number of epochs, and type of optimizers with an aim to find the best suited model. The models have been validated on publicly available chest X-ray images and the best performance is obtained by ResNet-34 with an accuracy of 98.33%. This study will be useful for researchers to think for the design of more effective CNN based models for early COVID-19 detection.
•A deep learning assisted automated method is proposed for COVID-19 diagnosis.•A comprehensive study among eight pre-trained CNN models is performed.•The impact of several hyper-parameters have been analyzed.•The best performing model is obtained and compared with the state-of-the-art methods.•The model could assist radiologists for accurate and stable COVID-19 diagnosis.
With the large amount of high-spatial resolution images now available, scene classification aimed at obtaining high-level semantic concepts has drawn great attention. The convolutional neural ...networks (CNNs), which are typical deep learning methods, have widely been studied to automatically learn features for the images for scene classification. However, scene classification based on CNNs is still difficult due to the scale variation of the objects in remote sensing imagery. In this paper, a multiscale CNN (MCNN) framework is proposed to solve the problem. In MCNN, a network structure containing dual branches of a fixed-scale net (F-net) and a varied-scale net (V-net) is constructed and the parameters are shared by the F-net and V-net. The images and their rescaled images are fed into the F-net and V-net, respectively, allowing us to simultaneously train the shared network weights on multiscale images. Furthermore, to ensure that the features extracted from MCNN are scale invariant, a similarity measure layer is added to MCNN, which forces the two feature vectors extracted from the image and its corresponding rescaled image to be as close as possible in the training phase. To demonstrate the effectiveness of the proposed method, we compared the results obtained using three widely used remote sensing data sets: the UC Merced data set, the aerial image data set, and the google data set of SIRI-WHU. The results confirm that the proposed method performs significantly better than the other state-of-the-art scene classification methods.
Fault detection and classification are considered as one of the most mandatory techniques in nowadays industrial monitoring. The necessity of fault monitoring is due to the fact that early detection ...can restrain high-cost maintenance. Due to the complexity of the wind turbines and the considerable amount of data available via SCADA systems, machine learning methods and specifically deep learning approaches seem to be powerful means to solve the problem of fault detection in wind turbines. In this article, a novel deep learning fault detection and classification method is presented based on the time-series analysis technique and convolutional neural networks (CNN) in order to deal with some classes of faults in wind turbine machines. To validate this approach, challenging scenarios, which consists of less than 5% performance reduction (which is hard to identify) in the two actuators or four sensors of the wind turbine along with sensors noise are investigated, and the appropriate structures of CNN are suggested. Finally, these algorithms are evaluated in simulation based on the data of a 4.8 MW wind turbine benchmark and their accuracy approves the convincing performance of the proposed methods. The proposed algorithm are applicable to both on-shore and off-shore wind turbine machines.
PDF
