Related papers: BiHDTrans: binary hyperdimensional transformer for…
In the field of medical imaging, AI-assisted techniques such as object detection, segmentation, and classification are widely employed to alleviate the workload of physicians and doctors. However, single-task models are predominantly used,…
In the application of brain-computer interface (BCI), being able to accurately decode brain signals is a critical task. For the multi-class classification task of brain signal ECoG, how to improve the classification accuracy is one of the…
Standard Test-Time Adaptation (TTA) methods typically treat inference as a blind optimization task, applying generic objectives to all or filtered test samples. In safety-critical medical segmentation, this lack of selectivity often causes…
Multi-modal Satellite Image Time Series (SITS) analysis faces significant computational challenges for live land monitoring applications. While Transformer architectures excel at capturing temporal dependencies and fusing multi-modal data,…
Hyperdimensional computing (HDC) is emerging as a promising AI approach that can effectively target TinyML applications thanks to its lightweight computing and memory requirements. Previous works on HDC showed that limiting the standard 10k…
This paper presents new hierarchically cascaded transformers that can improve data efficiency through attribute surrogates learning and spectral tokens pooling. Vision transformers have recently been thought of as a promising alternative to…
In recent years, the methods on matrix-based or bilinear discriminant analysis (BLDA) have received much attention. Despite their advantages, it has been reported that the traditional vector-based regularized LDA (RLDA) is still quite…
Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…
Human state recognition is a critical topic with pervasive and important applications in human-machine systems. Multi-modal fusion, the combination of metrics from multiple data sources, has been shown as a sound method for improving the…
We show how bidirectional transformers trained for masked token prediction can be applied to neural image compression to achieve state-of-the-art results. Such models were previously used for image generation by progressivly sampling groups…
LiDAR point cloud semantic segmentation plays a crucial role in autonomous driving. In recent years, semi-supervised methods have gained popularity due to their significant reduction in annotation labor and time costs. Current…
This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not…
Digital twins are transforming the way we monitor, analyze, and control physical systems, but designing architectures that balance real-time responsiveness with heavy computational demands remains a challenge. Cloud-based solutions often…
It is highly desired to operate a joint time and frequency transfer over the exiting fiber-optic telecom networks with the commercial data transmission. Previously, we proposed a time transfer scheme based on bidirectional time division…
Integral transforms are invaluable mathematical tools to map functions into spaces where they are easier to characterize. We introduce the hyperdimensional transform as a new kind of integral transform. It converts square-integrable…
Intrusion Detection Systems (IDSs) have played a significant role in the detection and prevention of cyber-attacks in traditional computing systems. It is not surprising that this technology is now being applied to secure Internet of Things…
Recent byte-level language models (LMs) match the performance of token-level models without relying on subword vocabularies, yet their utility is limited by slow, byte-by-byte autoregressive generation. We address this bottleneck in the…
LiDAR semantic segmentation plays a pivotal role in 3D scene understanding for edge applications such as autonomous driving. However, significant challenges remain for real-world deployments, particularly for on-device post-deployment…
Medical image classification has developed rapidly under the impetus of the convolutional neural network (CNN). Due to the fixed size of the receptive field of the convolution kernel, it is difficult to capture the global features of…
Decision trees and models that use them as primitives are workhorses of machine learning in Euclidean spaces. Recent work has further extended these models to the Lorentz model of hyperbolic space by replacing axis-parallel hyperplanes with…