Convolutional Neural Network's (CNN's) performance disparity on clean and corrupted datasets has recently come under scrutiny. In this work, we analyse common corruptions in the frequency domain, i.e., High Frequency corruptions (HFc, e.g., noise) and Low Frequency corruptions (LFc, e.g., blur). Although a simple solution to HFc is low-pass filtering, ReLU -- a widely used Activation Function (AF), does not have any filtering mechanism. In this work, we instill low-pass filtering into the AF (LP-ReLU) to improve robustness against HFc. To deal with LFc, we complement LP-ReLU with Discrete Cosine Transform based augmentation. LP-ReLU, coupled with DCT augmentation, enables a deep network to tackle the entire spectrum of corruption. We use CIFAR-10-C and Tiny ImageNet-C for evaluation and demonstrate improvements of 5% and 7.3% in accuracy respectively, compared to the State-Of-The-Art (SOTA). We further evaluate our method's stability on a variety of perturbations in CIFAR-10-P and Tiny ImageNet-P, achieving new SOTA in these experiments as well. To further strengthen our understanding regarding CNN's lack of robustness, a decision space visualisation process is proposed and presented in this work.
Indian Institute of Technology Indore（印度理工学院印多尔分校）
Breast cancer is becoming pervasive with each passing day. Hence, its early detection is a big step in saving the life of any patient. Mammography is a common tool in breast cancer diagnosis. The most important step here is classification of mammogram patches as normal-abnormal and benign-malignant. Texture of a breast in a mammogram patch plays a significant role in these classifications. We propose a variation of Histogram of Gradients (HOG) and Gabor filter combination called Histogram of Oriented Texture (HOT) that exploits this fact. We also revisit the Pass Band - Discrete Cosine Transfo…
This paper compares the performance of a NN taking the output of a DCT (Discrete Cosine Transform) of an image patch with leNet for classifying MNIST hand written digits. The basis functions underlying the DCT bear a passing resemblance to some of the learned basis function of the Visual Transformer but are an order of magnitude faster to apply.
Nowadays, commonly-used authentication systems for mobile device users, e.g. password checking, face recognition or fingerprint scanning, are susceptible to various kinds of attacks. In order to prevent some of the possible attacks, these explicit authentication systems can be enhanced by considering a two-factor authentication scheme, in which the second factor is an implicit authentication system based on analyzing motion sensor data captured by accelerometers or gyroscopes. In order to avoid any additional burdens to the user, the registration process of the implicit authentication system m…
Missouri State University（密苏里州立大学）；Tampere University（坦佩雷大学）
Bioimage classification plays a crucial role in many biological problems. In this work, we present a new General Purpose (GenP) ensemble that boosts performance by combining local features, dense sampling features, and deep learning approaches. First, we introduce three new methods for data augmentation based on PCA/DCT; second, we show that different data augmentation approaches can boost the performance of an ensemble of CNNs; and, finally, we propose a set of handcrafted/learned descriptors that are highly generalizable. Each handcrafted descriptor is used to train a different Support Vecto…
Classification of images within the compressed domain offers significant benefits. These benefits include reduced memory and computational requirements of a classification system. This paper proposes two such methods as a proof of concept: The first classifies within the JPEG image transform domain (i.e. DCT transform data); the second classifies the JPEG compressed binary bitstream directly. These two methods are implemented using Residual Network CNNs and an adapted Vision Transformer. Top-1 accuracy of approximately 70% and 60% were achieved using these methods respectively when classifying…
University of Padua（帕多瓦大学）；Tampere University（坦佩雷大学）；Missouri State University（密苏里州立大学）；Università di Bologna（博洛尼亚大学）
A problem with Convolutional Neural Networks (CNNs) is that they require large datasets to obtain adequate robustness; on small datasets, they are prone to overfitting. Many methods have been proposed to overcome this shortcoming with CNNs. In cases where additional samples cannot easily be collected, a common approach is to generate more data points from existing data using an augmentation technique. In image classification, many augmentation approaches utilize simple image manipulation algorithms. In this work, we build ensembles on the data level by adding images generated by combining four…
Tables are widely used in documents because of their compact and structured representation of information. In particular, in scientific papers, tables can sum up novel discoveries and summarize experimental results, making the research comparable and easily understandable by scholars. Since the layout of tables is highly variable, it would be useful to interpret their content and classify them into categories. This could be helpful to directly extract information from scientific papers, for instance comparing performance of some models given their paper result tables. In this work, we address …
Jadavpur University（贾达布尔大学）；Nanyang Technological University（南洋理工大学）；Cognizant Technology Solutions（高知特科技解决方案公司）；Indian Institute of Technology Roorkee（印度理工学院鲁尔基分校）
Binarization of degraded document images is an elementary step in most of the problems in document image analysis domain. The paper re-visits the binarization problem by introducing an adversarial learning approach. We construct a Texture Augmentation Network that transfers the texture element of a degraded reference document image to a clean binary image. In this way, the network creates multiple versions of the same textual content with various noisy textures, thus enlarging the available document binarization datasets. At last, the newly generated images are passed through a Binarization ne…
Nanyang Technological University（南洋理工大学）；Singapore Management University（新加坡管理大学）；Salesforce Research Asia（赛富时亚洲研究院）
This paper investigates an open research problem of generating text-image pairs to improve the training of fine-grained image-to-text cross-modal retrieval task, and proposes a novel framework for paired data augmentation by uncovering the hidden semantic information of StyleGAN2 model. Specifically, we first train a StyleGAN2 model on the given dataset. We then project the real images back to the latent space of StyleGAN2 to obtain the latent codes. To make the generated images manipulatable, we further introduce a latent space alignment module to learn the alignment between StyleGAN2 latent …
University of Burgundy（勃艮第大学）；Higher School of Technology（高等技术学院）；Faculty of Sciences, University of Mohammed V（穆罕默德五世大学理学院）
Due to the current progress in Internet, digital contents (video, audio and images) are widely used. Distribution of multimedia contents is now faster and it allows for easy unauthorized reproduction of information. Digital watermarking came up while trying to solve this problem. Its main idea is to embed a watermark into a host digital content without affecting its quality. Moreover, watermarking can be used in several applications such as authentication, copy control, indexation, Copyright protection, etc. In this paper, we propose a blind robust image watermarking approach as a solution to …
UC San Diego（加州大学圣地亚哥分校）；Toyota Collaborative Safety Research Center（丰田协作安全研究中心）
Understanding occupant-vehicle interactions by modeling control transitions is important to ensure safe approaches to passenger vehicle automation. Models which contain contextual, semantically meaningful representations of driver states can be used to determine the appropriate timing and conditions for transfer of control between driver and vehicle. However, such models rely on real-world control take-over data from drivers engaged in distracting activities, which is costly to collect. Here, we introduce a scheme for data augmentation for such a dataset. Using the augmented dataset, we develo…
Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external conditions can mislead the model. Test-Time Augmentation (TTA) techniques aim to alleviate such common side effect at inference-time, first running multiple feed-forward passes on a set of altered versions of the same input sample, and then computing the main outcome through a consensus of the aggregated predictions. Unfortunately, the implementation of TTA on…
ContextMix: A context-aware data augmentation method for industrial visual inspection systems
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Samsung Electro-Mechanics（三星电机）；LG AI Research（LG AI研究院）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；RPTU Kaiserslautern-Landau（凯泽斯劳滕-兰道大学）
This paper aims to design robust Edge Intelligence using semantic communication for time-critical IoT applications. We systematically analyze the effect of image DCT coefficients on inference accuracy and propose the channel-agnostic effectiveness encoding for offloading by transmitting the most meaningful task data first. This scheme can well utilize all available communication resource and strike a balance between transmission latency and inference accuracy. Then, we design an effectiveness decoding by implementing a novel image augmentation process for convolutional neural network (CNN) tra…
Medical Image Segmentation is a useful application for medical image analysis including detecting diseases and abnormalities in imaging modalities such as MRI, CT etc. Deep learning has proven to be promising for this task but usually has a low accuracy because of the lack of appropriate publicly available annotated or segmented medical datasets. In addition, the datasets that are available may have a different texture because of different dosage values or scanner properties than the images that need to be segmented. This paper presents a StyleGAN-driven approach for segmenting publicly availa…
Towards Autonomous Aircraft Surveillance from Nanosatellites through On-Board Inference and Generative Data Augmentation
Universidad de Castilla–La Mancha（卡斯蒂利亚-拉曼恰大学）；Universidad de Castilla-La Mancha（卡斯蒂利亚-拉曼恰大学）；Escuela de Ingeniería Industrial y Aeroespacial de Toledo（托莱多工业与航空航天工程学院）；Escuela Superior de Informática（高等信息学院）
