Related papers: Semantic Meta-Split Learning: A TinyML Scheme for …

Reliable classification and detection of certain medical conditions, in images, with state-of-the-art semantic segmentation networks, require vast amounts of pixel-wise annotation. However, the public availability of such datasets is…

In this work, we expand the cooperative multi-task semantic communication framework (CMT-SemCom) introduced in [1], which divides the semantic encoder on the transmitter side into a common unit (CU) and multiple specific units (SUs), to a…

Deep learning has achieved remarkable success in many machine learning tasks such as image classification, speech recognition, and game playing. However, these breakthroughs are often difficult to translate into real-world engineering…

This article studies the problem of image segmentation-based semantic communication in autonomous driving. In real traffic scenes, detecting the key objects (e.g., vehicles, pedestrians and obstacles) is more crucial than that of other…

Sensing and communication are fundamental enablers of next-generation networks. While communication technologies have advanced significantly, sensing remains limited to conventional parameter estimation and is far from fully explored.…

Recent years have witnessed the great progress of deep neural networks on semantic segmentation, particularly in medical imaging. Nevertheless, training high-performing models require large amounts of pixel-level ground truth masks, which…

Semantic communication is envisioned as a promising technique to break through the Shannon limit. However, semantic inference and semantic error correction have not been well studied. Moreover, error correction methods of existing semantic…

Meta-learning is a powerful paradigm for tackling few-shot tasks. However, recent studies indicate that models trained with the whole-class training strategy can achieve comparable performance to those trained with meta-learning in few-shot…

Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task, but they remain highly memory-intensive to train. This…

Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training. To address the above problem, we consider an efficient…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from limited labeled examples. Numerous methods for this task focus on utilizing the predictions of unlabeled instances consistency alone to…

Few-shot learning has been used to tackle the problem of label scarcity in text classification, of which meta-learning based methods have shown to be effective, such as the prototypical networks (PROTO). Despite the success of PROTO, there…

Few-shot Intent Detection is challenging due to the scarcity of available annotated utterances. Although recent works demonstrate that multi-level matching plays an important role in transferring learned knowledge from seen training classes…

Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research community has achieved promising results over the last five…

Teaching machines to recognize a new category based on few training samples especially only one remains challenging owing to the incomprehensive understanding of the novel category caused by the lack of data. However, human can learn new…

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…

In recent years, the demand of image compression models for machine vision has increased dramatically. However, the training frameworks of image compression still focus on the vision of human, maintaining the excessive perceptual details,…

Many meta-learning methods are proposed for few-shot detection. However, previous most methods have two main problems, poor detection APs, and strong bias because of imbalance and insufficient datasets. Previous works mainly alleviate these…

Spatial transcriptomics (ST) technologies enable gene expression profiling with spatial resolution, offering unprecedented insights into tissue organization and disease heterogeneity. However, current analysis methods often struggle with…

Focusing on the received power prediction of millimeter-wave (mmWave) radio-frequency (RF) signals, we propose a multimodal split learning (SL) framework that integrates RF received signal powers and depth-images observed by physically…