Related papers: sEMG-Based Joint Angle Estimation via Hierarchical…

Category-level pose estimation is a challenging problem due to intra-class shape variations. Recent methods deform pre-computed shape priors to map the observed point cloud into the normalized object coordinate space and then retrieve the…

The recent integration of attention mechanisms into segmentation networks improves their representational capabilities through a great emphasis on more informative features. However, these attention mechanisms ignore an implicit sub-task of…

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

ISAC enables pervasive monitoring, but modern sensing algorithms are often too complex for energy-constrained edge devices. This motivates the development of learning techniques that balance accuracy performance and energy efficiency.…

Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical adoption is limited by the computational overhead of deep…

Self-attention mechanism has been widely used for various tasks. It is designed to compute the representation of each position by a weighted sum of the features at all positions. Thus, it can capture long-range relations for computer vision…

Surface electromyography (sEMG) is a widely employed bio-signal that captures human muscle activity via electrodes placed on the skin. Several studies have proposed methods to remove sEMG contaminants, as non-invasive measurements render…

Deformable medical image registration aligns anatomical structures across images but remains computationally dense at 3D resolution. Spiking neural networks (SNNs) offer sparse event-driven computation, yet have not been systematically…

Spiking Neural Networks (SNNs) have a low-power advantage but perform poorly in image segmentation tasks. The reason is that directly converting neural networks with complex architectural designs for segmentation tasks into spiking versions…

Multi-exposure High Dynamic Range (HDR) imaging is a challenging task when facing truncated texture and complex motion. Existing deep learning-based methods have achieved great success by either following the alignment and fusion pipeline…

Purpose: To systematically investigate the influence of various data consistency layers, (semi-)supervised learning and ensembling strategies, defined in a $\Sigma$-net, for accelerated parallel MR image reconstruction using deep learning.…

Breast ultrasound imaging is a valuable tool for early breast cancer detection, but automated tumor segmentation is challenging due to inherent noise, variations in scale of lesions, and fuzzy boundaries. To address these challenges, we…

We study zero-shot anomaly detection and segmentation using frozen foundation model features, where all learnable parameters are trained only on a labeled auxiliary dataset and deployed to unseen target categories without any target-domain…

Spiking Neural Networks (SNNs) are efficient computation models to perform spatio-temporal pattern recognition on {resource}- and {power}-constrained platforms. SNNs executed on neuromorphic hardware can further reduce energy consumption of…

In this work, we propose to resolve the issue existing in current deep learning based organ segmentation systems that they often produce results that do not capture the overall shape of the target organ and often lack smoothness. Since…

Single-image super-resolution (SISR) has seen significant advancements through the integration of deep learning. However, the substantial computational and memory requirements of existing methods often limit their practical application.…

Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make edge deployment challenging. Although post-training quantization (PTQ) offers a promising compression…

Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, offer a distinctive approach for capturing the complexities of temporal data. However, their potential for spatial modeling in multivariate time-series…

Deep learning approaches for heart-sound (PCG) segmentation built on time-frequency features can be accurate but often rely on large expert-labeled datasets, limiting robustness and deployment. We present TopSeg, a topological…

Radio Frequency (RF) sensing holds the potential for enabling pervasive monitoring applications. However, modern sensing algorithms imply complex operations, which clash with the energy-constrained nature of edge sensing devices. This calls…