Related papers: TinyM$^2$Net: A Flexible System Algorithm Co-desig…
Multimodal learning is defined as learning over multiple heterogeneous input modalities such as video, audio, and text. In this work, we are concerned with understanding how models behave as the type of modalities differ between training…
Passive acoustic monitoring has become a key strategy in biodiversity assessment, conservation, and behavioral ecology, especially as Internet-of-Things (IoT) devices enable continuous in situ audio collection at scale. While recent…
As artificial intelligence systems increasingly operate in Real-world environments, the integration of multi-modal data sources such as vision, language, and audio presents both unprecedented opportunities and critical challenges for…
The burgeoning volume of digital content across diverse modalities necessitates efficient storage and retrieval methods. Conventional approaches struggle to cope with the escalating complexity and scale of multimedia data. In this paper, we…
Recent applications of deep convolutional neural networks in medical imaging raise concerns about their interpretability. While most explainable deep learning applications use post hoc methods (such as GradCAM) to generate feature…
Safe manipulation in unstructured environments for service robots is a challenging problem. A failure detection system is needed to monitor and detect unintended outcomes. We propose FINO-Net, a novel multimodal sensor fusion based deep…
Recent advances in large language models (LLMs) have generated great interest in their applications for IoT automation and device management. However, centralized approaches struggle to scale across heterogeneous, large-scale systems. We…
Automatic modulation classification (AMC) is an essential technique for noncooperative spectrum monitoring and intelligent wireless receivers. However, practical AMC models must identify modulation formats from short and noisy I/Q…
Detecting objects with visual sensors is crucial for numerous mobile robotics applications, from autonomous navigation to inspection. However, robots often need to operate under significant domains shifts from those they were trained in,…
In this work, we propose a novel meta-learning approach for few-shot classification, which learns transferable prior knowledge across tasks and directly produces network parameters for similar unseen tasks with training samples. Our…
Large-scale Internet of Things (IoT) networks enable intelligent services such as smart cities and autonomous driving, but often face resource constraints. Collecting heterogeneous sensory data, especially in small-scale datasets, is…
We present a novel, parameter-efficient and practical fully convolutional neural network architecture, termed InfiNet, aimed at voxel-wise semantic segmentation of infant brain MRI images at iso-intense stage, which can be easily extended…
Medical image segmentation, particularly tumor segmentation, is a critical task in medical imaging, with U-Net being a widely adopted convolutional neural network (CNN) architecture for this purpose. However, U-Net's high computational and…
Accurate multiple-input multiple-output (MIMO) channel estimation is critical for next-generation wireless systems, enabling enhanced communication and sensing performance. Traditional model-based channel estimation methods suffer, however,…
We present the TinyLLaVA framework that provides a unified perspective in designing and analyzing the small-scale Large Multimodal Models (LMMs). We empirically study the effects of different vision encoders, connection modules, language…
Connecting large libraries of digitized audio recordings to their corresponding sheet music images has long been a motivation for researchers to develop new cross-modal retrieval systems. In recent years, retrieval systems based on…
Previous industrial anomaly detection methods often struggle to handle the extensive diversity in training sets, particularly when they contain stylistically diverse and feature-rich samples, which we categorize as feature-rich anomaly…
Federated learning can be a promising solution for enabling IoT cybersecurity (i.e., anomaly detection in the IoT environment) while preserving data privacy and mitigating the high communication/storage overhead (e.g., high-frequency data…
This paper presents a comprehensive evaluation of lightweight deep learning models for image classification, emphasizing their suitability for deployment in resource-constrained environments such as low-memory devices. Five state-of-the-art…
Large language models (LLMs) have shown promising capabilities in visually interpreting medical time-series data. However, their general-purpose design can limit domain-specific precision, and the proprietary nature of many models poses…