Related papers: DEAL: Data-Efficient Adversarial Learning for High…

Thermographic photothermal super resolution reconstruction enables the resolution of internal defects/inhomogeneities below the classical limit which is governed by the diffusion properties of thermal wave propagation. Based on a…

Intermediate-level attacks that attempt to perturb feature representations following an adversarial direction drastically have shown favorable performance in crafting transferable adversarial examples. Existing methods in this category are…

Adversarial training has emerged as a key technique to enhance model robustness against adversarial input perturbations. Many of the existing methods rely on computationally expensive min-max problems that limit their application in…

Thermal analysis is crucial in 3D-IC design due to increased power density and complex heat dissipation paths. Although operator learning frameworks such as DeepOHeat~\cite{liu2023deepoheat} have demonstrated promising preliminary results…

Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations that preserve the semantics of the input, such as a change in…

RGB-Thermal (RGB-T) object detection utilizes thermal infrared (TIR) images to complement RGB data, improving robustness in challenging conditions. Traditional RGB-T detectors assume balanced training data, where both modalities contribute…

A human's attention can intuitively adapt to corrupted areas of an image by recalling a similar uncorrupted image they have previously seen. This observation motivates us to improve the attention of adversarial images by considering their…

Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence…

Underexposure regions are vital to construct a complete perception of the surroundings for safe autonomous driving. The availability of thermal cameras has provided an essential alternate to explore regions where other optical sensors lack…

Infrared image super-resolution (IISR) under real-world conditions is a practically significant yet rarely addressed task. Pioneering works are often trained and evaluated on simulated datasets or neglect the intrinsic differences between…

Climate simulations are essential in guiding our understanding of climate change and responding to its effects. However, it is computationally expensive to resolve complex climate processes at high spatial resolution. As one way to speed up…

Underwater images typically suffer from severe colour distortions, low visibility, and reduced structural clarity due to complex optical effects such as scattering and absorption, which greatly degrade their visual quality and limit the…

With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks against adversarial examples, imperceptibly perturbed inputs that…

Adversarial training is the most promising method for learning robust models against adversarial examples. A recent study has shown that knowledge distillation between the same architectures is effective in improving the performance of…

Image inpainting has achieved fundamental advances with deep learning. However, almost all existing inpainting methods aim to process natural images, while few target Thermal Infrared (TIR) images, which have widespread applications. When…

The hemorrhagic lesion segmentation plays a critical role in ophthalmic diagnosis, directly influencing early disease detection, treatment planning, and therapeutic efficacy evaluation. However, the task faces significant challenges due to…

Deep neural networks (DNNs) are sensitive to adversarial examples, resulting in fragile and unreliable performance in the real world. Although adversarial training (AT) is currently one of the most effective methodologies to robustify DNNs,…

Adverse weather severely impairs real-world visual perception, while existing vision models trained on synthetic data with fixed parameters struggle to generalize to complex degradations. To address this, we first construct HFLS-Weather, a…

Infrared image helps improve the perception capabilities of autonomous driving in complex weather conditions such as fog, rain, and low light. However, infrared image often suffers from low contrast, especially in non-heat-emitting targets…

Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is…