Previous few-shot learning (FSL) works mostly are limited to natural images of general concepts and categories. These works assume very high visual similarity between the source and target classes. In contrast, the recently proposed cross-domain few-shot learning (CD-FSL) aims at transferring knowledge from general nature images of many labeled examples to novel domain-specific target categories of only a few labeled examples. The key challenge of CD-FSL lies in the huge data shift between source and target domains, which is typically in the form of totally different visual styles. This makes it very nontrivial to directly extend the classical FSL methods to address the CD-FSL task. To this end, this paper studies the problem of CD-FSL by spanning the style distributions of the source dataset. Particularly, wavelet transform is introduced to enable the decomposition of visual representations into low-frequency components such as shape and style and high-frequency components e.g., texture. To make our model robust to visual styles, the source images are augmented by swapping the styles of their low-frequency components with each other. We propose a novel Style Augmentation (StyleAug) module to implement this idea. Furthermore, we present a Self-Supervised Learning (SSL) module to ensure the predictions of style-augmented images are semantically similar to the unchanged ones. This avoids the potential semantic drift problem in exchanging the styles. Extensive experiments on two CD-FSL benchmarks show the effectiveness of our method. Our codes and models will be released.
One of the biggest problems in neural learning networks is the lack of training data available to train the network. Data augmentation techniques over the past few years, have therefore been developed, aiming to increase the amount of artificial training data with the limited number of real world samples. In this paper, we look particularly at the MNIST handwritten dataset an image dataset used for digit recognition, and the methods of data augmentation done on this data set. We then take a detailed look into one of the most popular augmentation techniques used for this data set elastic deform…
Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；University of Science and Technology of China（中国科学技术大学）；OPPO Research Institute（OPPO研究院）；The Hong Kong Polytechnic University（香港理工大学）；ShanghaiTech University（上海科技大学）
Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain
Shanghai Jiao Tong University（上海交通大学）；Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS)（中国科学院智能信息处理重点实验室）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；Pengcheng Laboratory（鹏城实验室）；Alibaba Group（阿里巴巴集团）；Tsinghua University（清华大学）
Despite the remarkable success of deep learning in pattern recognition, deep network models face the problem of training a large number of parameters. In this paper, we propose and evaluate a novel multi-path wavelet neural network architecture for image classification with far less number of trainable parameters. The model architecture consists of a multi-path layout with several levels of wavelet decompositions performed in parallel followed by fully connected layers. These decomposition operations comprise wavelet neurons with learnable parameters, which are updated during the training phas…
Faculty of Mathematics and Computer Science（数学与计算机科学学院）；University of Havana（哈瓦那大学）
This paper presents and validates a novel lung nodule classification algorithm that uses multifractal features found in X-ray images. The proposed method includes a pre-processing step where two enhancement techniques are applied: histogram equalization and a combination of wavelet decomposition and morphological operations. As a novelty, multifractal features using wavelet leader based formalism are used with Support Vector Machine classifier; other classical texture features were also included. Best results were obtained when using multifractal features in combination with classical texture …
School of Electrical Engineering and Computer Science, National University of Sciences and Technology（国家科技大学 电气工程与计算机科学学院）；Information Technology University (ITU)-Punjab（旁遮普信息技术大学）；University of the West of England (UWE)（西英格兰大学）
Breast cancer is one of the most common cause of deaths among women. Mammography is a widely used imaging modality that can be used for cancer detection in its early stages. Deep learning is widely used for the detection of cancerous masses in the images obtained via mammography. The need to improve accuracy remains constant due to the sensitive nature of the datasets so we introduce segmentation and wavelet transform to enhance the important features in the image scans. Our proposed system aids the radiologist in the screening phase of cancer detection by using a combination of segmentation a…
German Aerospace Center (DLR)（德国航空航天中心（DLR））；Technical University of Munich（慕尼黑工业大学）
The knowledge about the placement and appearance of lane markings is a prerequisite for the creation of maps with high precision, necessary for autonomous driving, infrastructure monitoring, lane-wise traffic management, and urban planning. Lane markings are one of the important components of such maps. Lane markings convey the rules of roads to drivers. While these rules are learned by humans, an autonomous driving vehicle should be taught to learn them to localize itself. Therefore, accurate and reliable lane marking semantic segmentation in the imagery of roads and highways is needed to ach…
Recent research has proposed the use of Semi Adversarial Networks (SAN) for imparting privacy to face images. SANs are convolutional autoencoders that perturb face images such that the perturbed images cannot be reliably used by an attribute classifier (e.g., a gender classifier) but can still be used by a face matcher for matching purposes. However, the generalizability of SANs across multiple arbitrary gender classifiers has not been demonstrated in the literature. In this work, we tackle the generalization issue by designing an ensemble SAN model that generates a diverse set of perturbed ou…
Fudan University（复旦大学）；Shanghai Center for Brain Science and Brain-inspired Technology（上海脑科学与类脑研究中心）
There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as stroke is an important cerebrovascular disease. Although deep learning-based models have been proposed for this task, generalizing these models to unseen sites is difficult due to not only the large inter-site discrepancy among different scanners, imaging protocols, and populations, but also the variations in stroke lesion shape, size, and location. To tackle this issue, we introduce a self-adaptive normalization network, termed SAN-Net, to achieve adaptiv…
The Cyprus Institute（塞浦路斯研究所）；National and Kapodistrian University of Athens（雅典国立卡波季斯特里安大学）
In recent years, considerable advancements have been made in the area of Generative Adversarial Networks (GANs), particularly with the advent of style-based architectures that address many key shortcomings - both in terms of modeling capabilities and network interpretability. Despite these improvements, the adoption of such approaches in the domain of satellite imagery is not straightforward. Typical vision datasets used in generative tasks are well-aligned and annotated, and exhibit limited variability. In contrast, satellite imagery exhibits great spatial and spectral variability, wide prese…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Southwest Hospital（西南医院）；Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）
Deep learning holds great promise in the reconstruction of undersampled Magnetic Resonance Imaging (MRI) data, providing new opportunities to escalate the performance of rapid MRI. In existing deep learning-based reconstruction methods, supervised training is performed using artifact-free reference images and their corresponding undersampled pairs. The undersampled images are generated by a fixed undersampling pattern in the training, and the trained network is then applied to reconstruct new images acquired with the same pattern in the inference. While such a training strategy can maintain a …
Generative Priors for MRI Reconstruction Trained from Magnitude-Only Images Using Phase Augmentation
1 Institute for Diagnostic；Interventional Radiology, University Medical Center G\"ottingen, Germany 2 Institute of Biomedical Imaging, Graz University of Technology, Graz, Austria 3 Clinic for Neurology, University Medical Center Göttingen, Germany 4 German Centre for Cardiovascular Research (DZHK), partner site Lower Saxony, Germany 5 Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School
A Multi-Domain Feature Fusion Framework for Generalizable Deepfake Detection Across Different Generators
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad, Pakistan（巴基斯坦国立科技大学电气工程与计算机科学学院）；Department of Communication, Quality Management and Information Systems, Mid Sweden University, Ostersund Campus, Sweden（瑞典中部大学通信、质量管理和信息系统系，厄斯特松德校区）；Department of Computer Science, Electrical and Space Engineering, Lulea University of Technology, Luleå, Sweden（瑞典吕勒奥理工大学计算机科学、电气与空间工程系）
Single Image Super Resolution (SISR) techniques based on Super Resolution Convolutional Neural Networks (SRCNN) are applied to micro-computed tomography (μCT) images of sandstone and carbonate rocks. Digital rock imaging is limited by the capability of the scanning device resulting in trade-offs between resolution and field of view, and super resolution methods tested in this study aim to compensate for these limits. SRCNN models SR-Resnet, Enhanced Deep SR (EDSR), and Wide-Activation Deep SR (WDSR) are used on the Digital Rock Super Resolution 1 (DRSRD1) Dataset of 4x downsampled images, comp…
Northwestern Polytechnical University（西北工业大学）；Space and Upper Atmosphere Research Commission（空间与高层大气研究委员会）；National University of Computer and Emerging Sciences（国立计算机与新兴科学大学）
Image super-resolution (SR) is one of the vital image processing methods that improve the resolution of an image in the field of computer vision. In the last two decades, significant progress has been made in the field of super-resolution, especially by utilizing deep learning methods. This survey is an effort to provide a detailed survey of recent progress in single-image super-resolution in the perspective of deep learning while also informing about the initial classical methods used for image super-resolution. The survey classifies the image SR methods into four categories, i.e., classical …
