Related papers: DiffPerf: Towards Performance Differentiation and …

Following the recent success of deep neural networks (DNN) on video computer vision tasks, performing DNN inferences on videos that originate from mobile devices has gained practical significance. As such, previous approaches developed…

Stream Learning (SL) requires models that can quickly adapt to continuously evolving data, posing significant challenges in both computational efficiency and learning accuracy. Effective data selection is critical in SL to ensure a balance…

Deep neural networks (DNNs) have substantial computational requirements, which greatly limit their performance in resource-constrained environments. Recently, there are increasing efforts on optical neural networks and optical computing…

Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains hindered by substantial parameter counts, computational demands, and the probability of…

Under the ideal assumption of uniform propagation, cell-free massive MIMO (CF-mMIMO) provides uniformly high throughput over the network by effectively surrounding each user with its serving access point (AP) set. However, in realistic…

Diffusion models have garnered significant interest from the community for their great generative ability across various applications. However, their typical multi-step sequential-denoising nature gives rise to high cumulative latency,…

A limitation of bandwidth in the wireless network and the exponential rise in the high data rate requirement prompted the development of Massive Multiple-Input-Multiple-Output (MIMO) technique in 5G. Using this method the ever rising data…

Dynamic Adaptive Streaming over HTTP (DASH) is a recently proposed standard that offers different versions of the same media content to adapt the delivery process over the Internet to dynamic bandwidth fluctuations and different user device…

Data preprocessing is a crucial step in the machine learning process that transforms raw data into a more usable format for downstream ML models. However, it can be costly and time-consuming, often requiring the expertise of domain experts.…

The detection of manufacturing errors is crucial in fabrication processes to ensure product quality and safety standards. Since many defects occur very rarely and their characteristics are mostly unknown a priori, their detection is still…

Fairness is an important topic for medical image analysis, driven by the challenge of unbalanced training data among diverse target groups and the societal demand for equitable medical quality. In response to this issue, our research adopts…

The development of video diffusion models unveils a significant challenge: the substantial computational demands. To mitigate this challenge, we note that the reverse process of diffusion exhibits an inherent entropy-reducing nature. Given…

Diffusion-based data augmentation (DiffDA) has emerged as a promising approach to improving classification performance under data scarcity. However, existing works vary significantly in task configurations, model choices, and experimental…

Hyperspectral image classification (HSIC) has gained significant attention because of its potential in analyzing high-dimensional data with rich spectral and spatial information. In this work, we propose the Differential Spatial-Spectral…

With 5G networking, deterministic guarantees are emerging as a key enabler. In this context, we present a scalable Damper-based architecture for Large-scale Deterministic IP Networks (D-LDN) that meets required bounds on end-to-end delay…

In recent years, using a deep convolutional neural network (CNN) as a feature encoder (or backbone) is the most commonly observed architectural pattern in several computer vision methods, and semantic segmentation is no exception. The two…

Multimodal deep learning systems are deployed in dynamic scenarios due to the robustness afforded by multiple sensing modalities. Nevertheless, they struggle with varying compute resource availability (due to multi-tenancy, device…

Data preprocessing techniques are devoted to correct or alleviate errors in data. Discretization and feature selection are two of the most extended data preprocessing techniques. Although we can find many proposals for static Big Data…

We propose MaxDIRep, a domain adaptation method that improves the decomposition of data representations into domain-independent and domain-dependent components. Existing methods, such as Domain-Separation Networks (DSN), use a weak…

Users around the world face escalating network interference such as censorship, throttling, and interception, largely driven by the commoditization and growing availability of Deep Packet Inspection (DPI) devices. Once reserved for a few…