Sorry, you need to enable JavaScript to visit this website.

Sparse Modeling in Image Processing and Deep LearningSparse approximation is a well-established theory, with a profound impact on the fields of signal and image processing. In this talk we start by presenting this model and its features, and then turn to describe two special cases of it – the convolutional sparse coding (CSC) and its multi-layered version (ML-CSC).  Amazingly, as we will carefully show, ML-CSC provides a solid theoretical foundation to … deep-learning.

Supplemental for EVENT-BASED EGOCENTRIC HUMAN POSE ESTIMATION IN DYNAMIC ENVIRONMENT

Machine Unlearning addresses the challenge of efficiently removing the influence of specific data from ML models, in response to data privacy laws and user requests for data deletion. Beyond simply excluding data from the training set, unlearning requires erasing its effects on the model parameters. We present a novel unlearning framework Unlogit, that uses sensitivity-weighted adjustments in model logits to forget selected data.

Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive information leakage, and the creation of harmful or offensive content that could be exploited maliciously. In this study, we uncover a novel security threat where an attacker leverages diffusion model APIs to generate synthetic images, which are then used to train a high-performing substitute model.

The perception of strangeness or discomfort in virtual humans, as described by the Uncanny Valley (UV) theory, plays a critical role in shaping users’ interactions with technology. Understanding this phenomenon is essential to reduce its impact during the design and animation of virtual humans. While numerous studies have explored the subjective dimensions of the UV effect, focusing on human perception, our research proposes a novel methodology to investigate this phenomenon by correlating objective image character istics of virtual humans with users’ subjective perceptions of discomfort.

This study introduces an innovative framework for accurate colon segmentation in abdomen CT scans, addressing the unique challenges of this task. Our architecture enhances well-established 2D segmentation models by incorporating 3D contextual information through a novel method that generates an attention map for a given slice by considering its neighboring slices. This approach achieves effective colon segmentation without complex 3D convolutional neural networks (CNNs) or Long Short-Term Memory (LSTM) networks by combining 2D CNNs.

Cardiovascular diseases remain one of the leading causes of death worldwide. Therefore, developing and validating automated tools to help identify high-risk patients are of paramount clinical utility. In this article, we tackle this task and introduce a genetic programming algorithm (called GIRAFFE) to build (deep) machine learning classification ensembles for arrhythmia classification from two-dimensional images of 12-lead electrocardiogram (ECG) tracings.

Recently, nonnegative matrix factorization (NMF) has been widely adopted for community detection, because of its better interpretability. However, the existing NMF-based methods have the following three problems: 1) they directly transform the original network into community membership space, so it is difficult for them to capture the hierarchical information; 2) they often only pay attention to the topology of the network and ignore its node attributes; 3) it is hard for them to learn the global structure information necessary for community detection.

Recently, nonnegative matrix factorization (NMF) has been widely adopted for community detection, because of its better interpretability. However, the existing NMF-based methods have the following three problems: 1) they directly transform the original network into community membership space, so it is difficult for them to capture the hierarchical information; 2) they often only pay attention to the topology of the network and ignore its node attributes; 3) it is hard for them to learn the global structure information necessary for community detection.

Neuromorphic computing and, in particular, spiking neural networks (SNNs) have become an attractive alternative to deep neural networks for a broad range of signal processing applications, processing static and/or temporal inputs from different sensory modalities, including audio and vision sensors. In this paper, we start with a description of recent advances in algorithmic and optimization innovations to efficiently train and scale low-latency, and energy-efficient spiking neural networks (SNNs) for complex machine learning applications.