Related papers: Physics-Grounded Adversarial Stain Augmentation wi…

This paper revisits the simple, long-studied, yet still unsolved problem of making image classifiers robust to imperceptible perturbations. Taking CIFAR10 as an example, SOTA clean accuracy is about $100$%, but SOTA robustness to…

Millimeter-wave (mmWave) Radar--Camera fusion improves perception under adverse illumination and weather, but its performance is sensitive to Radar--Camera extrinsic calibration: residual misalignment biases Radar-to-image projection and…

Adversarial examples generated from surrogate models often possess the ability to deceive other black-box models, a property known as transferability. Recent research has focused on enhancing adversarial transferability, with input…

Generative adversarial networks (GANs) are one of the most powerful generative models, but always require a large and balanced dataset to train. Traditional GANs are not applicable to generate minority-class images in a highly imbalanced…

Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing…

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

The availability of training data is one of the main limitations in deep learning applications for medical imaging. Data augmentation is a popular approach to overcome this problem. A new approach is a Machine Learning based augmentation,…

We propose an efficient and generative augmentation approach to solve the inadequacy concern of underwater debris data for visual detection. We use cycleGAN as a data augmentation technique to convert openly available, abundant data of…

Adversarial training has been widely acknowledged as the most effective method to improve the adversarial robustness against adversarial examples for Deep Neural Networks (DNNs). So far, most existing works focus on enhancing the overall…

Compared to hematoxylin-eosin (H&E) staining, immunohistochemistry (IHC) not only maintains the structural features of tissue samples, but also provides high-resolution protein localization, which is essential for aiding in pathology…

Foundation diffusion models can generate photorealistic natural images, but adapting them to medical imaging remains challenging. In medical adaptation, limited labeled data can exacerbate hallucination-like and clinically implausible…

Driven by recent vision and graphics applications such as image segmentation and object recognition, computing pixel-accurate saliency values to uniformly highlight foreground objects becomes increasingly important. In this paper, we…

Immunohistochemical (IHC) staining provides crucial molecular characterization of tissue samples and plays an indispensable role in the clinical examination and diagnosis of cancers. However, compared with the commonly used Hematoxylin and…

Generative Adversarial Networks (GANs) have demonstrated their versatility across various applications, including data augmentation and malware detection. This research explores the effectiveness of utilizing GAN-generated data to train a…

Data augmentation has been widely employed to improve the generalization of deep neural networks. Most existing methods apply fixed or random transformations. However, we find that sample difficulty evolves along with the model's…

Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the…

Q-learning algorithms are appealing for real-world applications due to their data-efficiency, but they are very prone to overfitting and training instabilities when trained from visual observations. Prior work, namely SVEA, finds that…

Deep learning models are challenged by the distribution shift between the training data and test data. Recently, the large models pre-trained on diverse data have demonstrated unprecedented robustness to various distribution shifts.…

Supervised deep learning relies on the assumption that enough training data is available, which presents a problem for its application to several fields, like medical imaging. On the example of a binary image classification task (breast…

In computational pathology, deep learning (DL) models for tasks such as segmentation or tissue classification are known to suffer from domain shifts due to different staining techniques. Stain adaptation aims to reduce the generalization…