Related papers: Robust RF Data Normalization for Deep Learning

Deep neural networks are incredibly vulnerable to crafted, human-imperceptible adversarial perturbations. Although adversarial training (AT) has proven to be an effective defense approach, we find that the AT-trained models heavily rely on…

Deep learning (DL) algorithms have shown significant performance in various computer vision tasks. However, having limited labelled data lead to a network overfitting problem, where network performance is bad on unseen data as compared to…

Neural networks are prone to learn easy solutions from superficial statistics in the data, namely shortcut learning, which impairs generalization and robustness of models. We propose a data augmentation strategy, named DFM-X, that leverages…

Hyperspectral imaging provides detailed information about the scanned objects, as it captures their spectral characteristics within a large number of wavelength bands. Classification of such data has become an active research topic due to…

Data augmentation is widely utilized as an effective technique to enhance the generalization performance of deep models. However, data augmentation may inevitably introduce distribution shifts and noises, which significantly constrain the…

Deep learning-based blind image deblurring plays an essential role in solving image blur since all existing kernels are limited in modeling the real world blur. Thus far, researchers focus on powerful models to handle the deblurring problem…

Re-initializing a neural network during training has been observed to improve generalization in recent works. Yet it is neither widely adopted in deep learning practice nor is it often used in state-of-the-art training protocols. This…

Convolutional neural networks have demonstrated impressive results in many computer vision tasks. However, the increasing size of these networks raises concerns about the information overload resulting from the large number of network…

Research studies have shown no qualms about using data driven deep learning models for downstream tasks in medical image analysis, e.g., anatomy segmentation and lesion detection, disease diagnosis and prognosis, and treatment planning.…

Recent work has empirically shown that deep neural networks latch on to the Fourier statistics of training data and show increased sensitivity to Fourier-basis directions in the input. Understanding and modifying this Fourier-sensitivity of…

The crucial components of a conventional image registration method are the choice of the right feature representations and similarity measures. These two components, although elaborately designed, are somewhat handcrafted using human…

Deep neural networks have had an enormous impact on image analysis. State-of-the-art training methods, based on weight decay and DropOut, result in impressive performance when a very large training set is available. However, they tend to…

Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new possibilities for data compression, allowing compression…

Including information from additional spectral bands (e.g., near-infrared) can improve deep learning model performance for many vision-oriented tasks. There are many possible ways to incorporate this additional information into a deep…

One of the frequently stated advantages of neural networks is that they can work effectively with non-normally distributed data. But optimal results are possible with normalized data.In this paper, how normality of the input affects the…

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and…

The ability of neural radiance fields or NeRFs to conduct accurate 3D modelling has motivated application of the technique to scene representation. Previous approaches have mainly followed a centralised learning paradigm, which assumes that…

Increasing data volumes delivered by a new generation of radio interferometers require computationally efficient and robust calibration algorithms. In this paper, we propose distributed calibration as a way of improving both computational…

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that…