Related papers: Adversarial Soft-detection-based Aggregation Netwo…

Automatic building extraction from aerial imagery has several applications in urban planning, disaster management, and change detection. In recent years, several works have adopted deep convolutional neural networks (CNNs) for building…

Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable to adversarial attacks, which can cause incorrect…

Contemporary deep learning based medical image segmentation algorithms require hours of annotation labor by domain experts. These data hungry deep models perform sub-optimally in the presence of limited amount of labeled data. In this…

Data augmentation (DA) has been widely utilized to improve generalization in training deep neural networks. Recently, human-designed data augmentation has been gradually replaced by automatically learned augmentation policy. Through finding…

Object recognition from images means to automatically find object(s) of interest and to return their category and location information. Benefiting from research on deep learning, like convolutional neural networks~(CNNs) and generative…

Adversarial attacks meticulously generate minuscule, imperceptible perturbations to images to deceive neural networks. Counteracting these, adversarial purification methods seek to transform adversarial input samples into clean output…

The gap between sensing patterns of different face modalities remains a challenging problem in heterogeneous face recognition (HFR). This paper proposes an adversarial discriminative feature learning framework to close the sensing gap via…

Discriminative features play an important role in image and object classification and also in other fields of research such as semi-supervised learning, fine-grained classification, out of distribution detection. Inspired by Linear…

We present a new deep supervised learning method for intrinsic decomposition of a single image into its albedo and shading components. Our contributions are based on a new fully convolutional neural network that estimates absolute albedo…

Existing unsupervised methods have addressed the challenges of inconsistent paired data and tedious acquisition of ground-truth labels in shadow removal tasks. However, GAN-based training often faces issues such as mode collapse and…

We propose LSDAT, an image-agnostic decision-based black-box attack that exploits low-rank and sparse decomposition (LSD) to dramatically reduce the number of queries and achieve superior fooling rates compared to the state-of-the-art…

We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain alignment and importance…

Understanding and extracting 3D information of objects from monocular 2D images is a fundamental problem in computer vision. In the task of 3D object pose estimation, recent data driven deep neural network based approaches suffer from…

We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to…

Unsupervised domain adaptation (UDA) aims to transfer a model learned using labeled data from the source domain to unlabeled data in the target domain. To address the large domain gap issue between the source and target domains, we propose…

Deep neural network (DNN) models have proven to be vulnerable to adversarial digital and physical attacks. In this paper, we propose a novel attack- and dataset-agnostic and real-time detector for both types of adversarial inputs to…

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density…

The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's…

We describe a new approach that improves the training of generative adversarial nets (GANs) for synthesizing diverse images from a text input. Our approach is based on the conditional version of GANs and expands on previous work leveraging…

Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors. To…