Related papers: Fusion-ResNet: A Lightweight multi-label NILM Mode…

The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles. Quantization is a powerful tool to address the growing computational cost…

Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple…

In this paper, we investigate the challenges of complementary-label learning (CLL), a specialized form of weakly-supervised learning (WSL) where models are trained with labels indicating classes to which instances do not belong, rather than…

Non-intrusive load monitoring or energy disaggregation involves estimating the power consumption of individual appliances from measurements of the total power consumption of a home. Deep neural networks have been shown to be effective for…

The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite…

Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as image retrieval and medical imaging. Therefore, this paper…

Federated multi-view clustering offers the potential to develop a global clustering model using data distributed across multiple devices. However, current methods face challenges due to the absence of label information and the paramount…

3D anomaly detection is an emerging and vital computer vision task in industrial manufacturing (IM). Recently many advanced algorithms have been published, but most of them cannot meet the needs of IM. There are several disadvantages: i)…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

The current state-of-the-art No-Reference Image Quality Assessment (NR-IQA) methods typically rely on feature extraction from upstream semantic backbone networks, assuming that all extracted features are relevant. However, we make a key…

Short-term load forecasting for AI data centers presents new challenges because it is computing-driven, with heterogeneous job arrivals, sizes, and durations exhibiting bursty, non-stationary dynamics. Compared with traditional load types,…

Salient Object Detection (SOD) with deep learning often requires substantial computational resources and large annotated datasets, making it impractical for resource-constrained applications. Lightweight models address computational demands…

The deployment of AI models on low-power, real-time edge devices requires accelerators for which energy, latency, and area are all first-order concerns. There are many approaches to enabling deep neural networks (DNNs) in this domain,…

Existing multi-modal approaches primarily focus on enhancing multi-label skin lesion classification performance through advanced fusion modules, often neglecting the associated rise in parameters. In clinical settings, both clinical and…

This paper presents a novel Sequence-to-Sequence (Seq2Seq) model based on a transformer-based attention mechanism and temporal pooling for Non-Intrusive Load Monitoring (NILM) of smart buildings. The paper aims to improve the accuracy of…

Publicly available full-field digital mammography (FFDM) datasets remain limited in size, clinical annotations, and vendor diversity, hindering the development of robust models. We introduce LUMINA, a curated, multi-vendor FFDM dataset that…

Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this paper proposes a conceptually simple yet efficient training…

Computing-in-memory (CIM) is renowned in deep learning due to its high energy efficiency resulting from highly parallel computing with minimal data movement. However, current SRAM-based CIM designs suffer from long latency for loading…

Modern Artificial Intelligence (AI) applications are increasingly utilizing multi-tenant deep neural networks (DNNs), which lead to a significant rise in computing complexity and the need for computing parallelism. ReRAM-based…

Accurate classification of multipartite entanglement in high-dimensional quantum systems is crucial for advancing quantum communication and information processing. However, conventional methods are resource-intensive, and even many…