Related papers: LSOR: Longitudinally-Consistent Self-Organized Rep…

Self-Organizing Maps (SOM) are a classical method for unsupervised learning, vector quantization, and topographic mapping of high-dimensional data. However, existing SOM formulations often involve a trade-off between computational…

LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent…

Morphological methods play a crucial role in remote sensing image processing, due to their ability to capture and preserve small structural details. However, most of the existing deep learning models for semantic segmentation are based on…

We attack the problem of learning concepts automatically from noisy web image search results. Going beyond low level attributes, such as colour and texture, we explore weakly-labelled datasets for the learning of higher level concepts, such…

Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that methods for learning these representations are either…

Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically…

Deep Learning in Image Registration (DLIR) methods have been tremendously successful in image registration due to their speed and ability to incorporate weak label supervision at training time. However, existing DLIR methods forego many of…

Recent years have seen a surge in research on deep interpretable neural networks with decision trees as one of the most commonly incorporated tools. There are at least three advantages of using decision trees over logistic regression…

Longitudinal assessment of brain atrophy, particularly in the hippocampus, is a well-studied biomarker for neurodegenerative diseases, such as Alzheimer's disease (AD). In clinical trials, estimation of brain progressive rates can be…

This work introduces a novel generative continual learning framework based on self-organizing maps (SOMs) and variational autoencoders (VAEs) to enable memory-efficient replay, eliminating the need to store raw data samples or task labels.…

In this paper, we introduce an uplifted reduced order modeling (UROM) approach through the integration of standard projection based methods with long short-term memory (LSTM) embedding. Our approach has three modeling layers or components.…

Single image super-resolution (SISR) is of great importance as a low-level computer vision task. The fast development of Generative Adversarial Network (GAN) based deep learning architectures realises an efficient and effective SISR to…

The study of neurodegenerative diseases relies on the reconstruction and analysis of the brain cortex from magnetic resonance imaging (MRI). Traditional frameworks for this task like FreeSurfer demand lengthy runtimes, while its accelerated…

In recent years, deep learning has presented a great advance in hyperspectral image (HSI) classification. Particularly, long short-term memory (LSTM), as a special deep learning structure, has shown great ability in modeling long-term…

Accurate identification of late-life depression (LLD) using structural brain MRI is essential for monitoring disease progression and facilitating timely intervention. However, existing learning-based approaches for LLD detection are often…

Magnetic Resonance Imaging (MRI) provides detailed structural information, while functional MRI (fMRI) captures temporal brain activity. In this work, we present a multimodal deep learning framework that integrates MRI and fMRI for…

Region representation learning plays a pivotal role in urban computing by extracting meaningful features from unlabeled urban data. Analogous to how perceived facial age reflects an individual's health, the visual appearance of a city…

Monocular depth estimation is a challenging task that aims to predict a corresponding depth map from a given single RGB image. Recent deep learning models have been proposed to predict the depth from the image by learning the alignment of…

This study presents an innovative method for Alzheimer's disease diagnosis using 3D MRI designed to enhance the explainability of model decisions. Our approach adopts a soft attention mechanism, enabling 2D CNNs to extract volumetric…

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…