Related papers: Features-over-the-Air: Contrastive Learning Enable…

Traditional object detection methods face performance degradation challenges in complex scenarios such as low-light conditions and heavy occlusions due to a lack of high-level semantic understanding. To address this, this paper proposes an…

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…

Multi-label image recognition with incomplete labels is a challenging yet vital task in computer vision, which faces two fundamental challenges: learning semantic-aware features and recovering missing labels. In this paper, we propose a…

Collecting a large number of reliable training images annotated by multiple land-cover class labels in the framework of multi-label classification is time-consuming and costly in remote sensing (RS). To address this problem, publicly…

Federated learning (FL) is an emerging machine learning technique that aggregates model attributes from a large number of distributed devices. Several unique features such as energy saving and privacy preserving make FL a highly promising…

This paper considers the coexistence of Ultra Reliable Low Latency Communications (URLLC) and enhanced Mobile BroadBand (eMBB) services in the uplink of Cloud Radio Access Network (C-RAN) architecture based on the relaying of radio signals…

Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between two views of an image. NCE uses randomly sampled negative…

A non-orthogonal multiple access (NOMA) empowered integrated sensing and communication (ISAC) framework is investigated. A dual-functional base station serves multiple communication users employing NOMA, while the superimposed NOMA…

Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when applied to…

In this paper, we consider communication-efficient over-the-air federated learning (FL), where multiple edge devices with non-independent and identically distributed datasets perform multiple local iterations in each communication round and…

A novel non-orthogonal multiple access (NOMA) based cache-aided mobile edge computing (MEC) framework is proposed. For the purpose of efficiently allocating communication and computation resources to users' computation tasks requests, we…

Recent years, graph contrastive learning (GCL), which aims to learn representations from unlabeled graphs, has made great progress. However, the existing GCL methods mostly adopt human-designed graph augmentations, which are sensitive to…

In real-world datasets, noisy labels are pervasive. The challenge of learning with noisy labels (LNL) is to train a classifier that discerns the actual classes from given instances. For this, the model must identify features indicative of…

Task-oriented communication presents a promising approach to improve the communication efficiency of edge inference systems by optimizing learning-based modules to extract and transmit relevant task information. However, real-time…

In this paper, we jointly combine image classification and image denoising, aiming to enhance human perception of noisy images captured by edge devices, like low-light security cameras. In such settings, it is important to retain the…

Large language models (LLMs) have demonstrated remarkable success across various application domains, but their enormous sizes and computational demands pose significant challenges for deployment on resource-constrained edge devices. To…

Contrastive language--audio pretraining (CLAP) has achieved remarkable success as an audio--text embedding framework, but existing approaches are limited to monaural or single-source conditions and cannot fully capture spatial information.…

Contrastive learning (CL) has become a ubiquitous approach for several natural language processing (NLP) downstream tasks, especially for question answering (QA). However, the major challenge, how to efficiently train the knowledge…

Perfect alignment in chosen beam sectors at both transmit- and receive-nodes is required for beamforming in mmWave bands. Current 802.11ad WiFi and emerging 5G cellular standards spend up to several milliseconds exploring different sector…

Integrated learning and communication (ILAC) unifies learned transceivers with radio resource management, where semantic feature multiple access (SFMA) enables paired users to superpose their learned representations over shared…