Related papers: A Theoretically-Grounded Codebook for Digital Sema…
Recently, increasing attention has been drawn to training semantic segmentation models using synthetic data and computer-generated annotation. However, domain gap remains a major barrier and prevents models learned from synthetic data from…
This paper investigates distributed source-channel coding for correlated image semantic transmission over wireless channels. In this setup, correlated images at different transmitters are separately encoded and transmitted through dedicated…
Semantic communication systems for goal-oriented transmission must protect task-relevant information not only through source compression but also via physical layer mapping. Existing approaches decouple constellation design and semantic…
We focus on tackling weakly supervised semantic segmentation with scribble-level annotation. The regularized loss has been proven to be an effective solution for this task. However, most existing regularized losses only leverage static…
The last seventy years have witnessed the transition of communication from Shannon's theoretical concept to current high-efficient practical systems. Classical communication systems address the capability-deficiency issue mainly by…
Semantic communication, notable for ensuring quality of service by jointly optimizing source and channel coding, effectively extracts data semantics, reduces transmission length, and mitigates channel noise. However, most studies overlook…
Different from data-oriented communication systems that primarily focus on how to accurately transmit every bit of data, task-oriented semantic communication systems only transmit the specific semantic information required by downstream…
In this paper, we propose Conceptual Codebook Learning (CoCoLe), a novel fine-tuning method for vision-language models (VLMs) to address the challenge of improving the generalization capability of VLMs while fine-tuning them on downstream…
This report investigates enhancing semantic caching effectiveness by employing specialized, fine-tuned embedding models. Semantic caching relies on embedding similarity rather than exact key matching, presenting unique challenges in…
Semantic parsing aims at mapping natural language utterances into structured meaning representations. In this work, we propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages. Given an…
We investigate the application of semantic information theory to drug delivery systems (DDS) within the molecular communication (MC) framework. To operationalise this, we observe a DDS as a molecular concentration-based channel. Semantic…
Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…
The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segmentation tasks. To counter this challenge, we introduce an…
With the recent advancements in edge artificial intelligence (AI), future sixth-generation (6G) networks need to support new AI tasks such as classification and clustering apart from data recovery. Motivated by the success of deep learning,…
Quantum dense coding is one of the most important protocols in quantum communication. It derives from the idea of using quantum resources to boost the communication capacity and now serves as a key primitive across a variety of quantum…
Semantic parsing is a technique aimed at constructing a structured representation of the meaning of a natural-language question. Recent advancements in few-shot language models trained on code have demonstrated superior performance in…
This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures…
Semantic mapping is the incremental process of "mapping" relevant information of the world (i.e., spatial information, temporal events, agents and actions) to a formal description supported by a reasoning engine. Current research focuses on…
Communication with the goal of accurately conveying meaning, rather than accurately transmitting symbols, has become an area of growing interest. This paradigm, termed semantic communication, typically leverages modern developments in…
To improve communication efficiency and provide more useful information, we need to measure semantic information by combining inaccuracy or distortion, freshness, purposiveness, and efficiency. The author proposed the semantic information G…