Related papers: Faster ISNet for Background Bias Mitigation on Dee…

A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it lacks the capacity to resolve. We propose Data Warmup, a…

Despite being the cornerstone of deep learning, backpropagation is criticized for its inherent sequentiality, which can limit the scalability of very deep models. Such models faced convergence issues due to vanishing gradient, later…

Hyperspectral image (HSI) denoising is a crucial preprocessing step for subsequent tasks. The clean HSI usually reside in a low-dimensional subspace, which can be captured by low-rank and sparse representation, known as the physical prior…

Recently, deep learning has started to play an essential role in healthcare applications, including image search in digital pathology. Despite the recent progress in computer vision, significant issues remain for image searching in…

Deep learning based methods have achieved remarkable success in image restoration and enhancement, but most such methods rely on RGB input images. These methods fail to take into account the rich spectral distribution of natural images. We…

Deep learning models have demonstrated remarkable capabilities in learning complex patterns and concepts from training data. However, recent findings indicate that these models tend to rely heavily on simple and easily discernible features…

Hypergraphs offer a generalized framework for capturing high-order relationships between entities and have been widely applied in various domains, including healthcare, social networks, and bioinformatics. Hypergraph neural networks, which…

We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. Regularization is key in deep learning, especially when training complex models on relatively small…

Interpreting complex neural networks is crucial for understanding their decision-making processes, particularly in applications where transparency and accountability are essential. This proposed method addresses this need by focusing on…

Enforcing orthonormal or isometric property for the weight matrices has been shown to enhance the training of deep neural networks by mitigating gradient exploding/vanishing and increasing the robustness of the learned networks. However,…

Editing High Dynamic Range (HDR) environment maps using an inverse differentiable rendering architecture is a complex inverse problem due to the sparsity of relevant pixels and the challenges in balancing light sources and background. The…

We focus on the real-world problem of training accurate deep models for image classification of a small number of rare categories. In these scenarios, almost all images belong to the background category in the dataset (>95% of the dataset…

Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training. Learning rate schedules are widely used in real practice to adjust the learning rate according to pre-defined schedules…

Simplicity bias is the concerning tendency of deep networks to over-depend on simple, weakly predictive features, to the exclusion of stronger, more complex features. This is exacerbated in real-world applications by limited training data…

Neural networks are increasingly used as fast surrogate models across various domains, but unconstrained predictions can violate physical, operational, or safety requirements. We propose SnareNet, a feasibility-controlled architecture to…

Models for fine-grained image classification tasks, where the difference between some classes can be extremely subtle and the number of samples per class tends to be low, are particularly prone to picking up background-related biases and…

One of the main challenges since the advancement of convolutional neural networks is how to connect the extracted feature map to the final classification layer. VGG models used two sets of fully connected layers for the classification part…

Works on implicit regularization have studied gradient trajectories during the optimization process to explain why deep networks favor certain kinds of solutions over others. In deep linear networks, it has been shown that gradient descent…

In this paper, we propose using Learning from Answer Sets to approximate black-box models, such as Neural Networks (NN), in the specific case of learning user preferences. We specifically explore the use of ILASP (Inductive Learning of…

Hypernetworks, neural networks that predict the parameters of another neural network, are powerful models that have been successfully used in diverse applications from image generation to multi-task learning. Unfortunately, existing…