Related papers: LossLens: Diagnostics for Machine Learning through…

One of the main challenges in modern deep learning is to understand why such over-parameterized models perform so well when trained on finite data. A way to analyze this generalization concept is through the properties of the associated…

Knowledge about historic landslide event occurrence is important for supporting disaster risk reduction strategies. Building upon findings from 2022 Landslide4Sense Competition, we propose a deep neural network based system for landslide…

Real-time visibility determination in expansive or dynamically changing environments has long posed a significant challenge in computer graphics. Existing techniques are computationally expensive and often applied as a precomputation step…

Traditionally, neighborhood studies have used interviews, surveys, and manual image annotation guided by detailed protocols to identify environmental characteristics, including physical disorder, decay, street safety, and sociocultural…

Big-data-based artificial intelligence (AI) supports profound evolution in almost all of science and technology. However, modeling and forecasting multi-physical systems remain a challenge due to unavoidable data scarcity and noise.…

Salient object detection, which aims to identify and locate the most salient pixels or regions in images, has been attracting more and more interest due to its various real-world applications. However, this vision task is quite challenging,…

Understanding the behaviour of complex laser systems is an outstanding challenge, especially in the presence of nonlinear interactions between modes. Hidden features, such as the gain distributions and spatial localisation of lasing modes,…

The ability to explain decisions made by machine learning models remains one of the most significant hurdles towards widespread adoption of AI in highly sensitive areas such as medicine, cybersecurity or autonomous driving. Great interest…

Machine Unlearning aims to remove undesired information from trained models without requiring full retraining from scratch. Despite recent advancements, their underlying loss landscapes and optimization dynamics received less attention. In…

We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from $\mathbb{R}^n$ to $\mathbb{R}$ - in particular,…

Deep learning has achieved notable performance in the denoising task of low-quality medical images and the detection task of lesions, respectively. However, existing low-quality medical image denoising approaches are disconnected from the…

Current research in Computer Vision has shown that Convolutional Neural Networks (CNN) give state-of-the-art performance in many classification tasks and Computer Vision problems. The embedding of CNN, which is the internal representation…

Vision and language navigation (VLN) is a challenging visually-grounded language understanding task. Given a natural language navigation instruction, a visual agent interacts with a graph-based environment equipped with panorama images and…

We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the "learning to search" (L2S) approach to structured prediction. RNNs have been widely successful in structured prediction applications such as…

Deep learning involves navigating a high-dimensional loss landscape over the neural network parameter space. Over the course of training, complex computational structures form and re-form inside the neural network, leading to shifts in…

Low-light image enhancement remains a challenging task, particularly in the absence of paired training data. In this study, we present LucentVisionNet, a novel zero-shot learning framework that addresses the limitations of traditional and…

Lensless imaging stands out as a promising alternative to conventional lens-based systems, particularly in scenarios demanding ultracompact form factors and cost-effective architectures. However, such systems are fundamentally governed by…

We discuss several aspects of the loss landscape of regularized neural networks: the structure of stationary points, connectivity of optimal solutions, path with nonincreasing loss to arbitrary global optimum, and the nonuniqueness of…

In recent years, machine learning (ML) has gained significant popularity in the field of chemical informatics and electronic structure theory. These techniques often require researchers to engineer abstract "features" that encode chemical…

Capturing long-range dependencies in feature representations is crucial for many visual recognition tasks. Despite recent successes of deep convolutional networks, it remains challenging to model non-local context relations between visual…