Related papers: Cross Z-Complementary Pairs for Optimal Training i…

Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In this paper, we propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL), which combines the well-known contrastive loss…

There has been an increasing interest in harnessing deep learning to tackle combinatorial optimization (CO) problems in recent years. Typical CO deep learning approaches leverage the problem structure in the model architecture.…

Correlation filters (CFs) are a class of classifiers that are attractive for object localization and tracking applications. Traditionally, CFs have been designed in the frequency domain using the discrete Fourier transform (DFT), where…

This paper investigates the feasibility of machine learning (ML)-based pilotless spatial multiplexing in multiple-input and multiple-output (MIMO) communication systems. Especially, it is shown that by training the transmitter and receiver…

Automatic modulation classification (AMC) is an essential technique for noncooperative spectrum monitoring and intelligent wireless receivers. However, practical AMC models must identify modulation formats from short and noisy I/Q…

Feeding power amplifiers (PAs) with constant envelope (CE) signals is an effective way to reduce the power consumption in massive multiple-input-multiple-output (MIMO) systems. The nonlinear distortion caused by CE signaling must be…

Vision-language models (VLMs) pre-trained at large scale have shown unprecedented transferability capabilities and are being progressively integrated into medical image analysis. Although its discriminative potential has been widely…

Most of existing rendezvous algorithms generate channel-hopping sequences based on the whole channel set. They are inefficient when the set of available channels is a small subset of the whole channel set. We propose a new algorithm called…

End-to-end deep networks represent the state of the art for stereo matching. While excelling on images framing environments similar to the training set, major drops in accuracy occur in unseen domains (e.g., when moving from synthetic to…

Zero-shot 3D (ZS-3D) anomaly detection aims to identify defects in 3D objects without relying on labeled training data, making it especially valuable in scenarios constrained by data scarcity, privacy, or high annotation cost. However, most…

Compositional Zero-Shot Learning (CZSL) aims to recognize novel attribute-object compositions based on the knowledge learned from seen ones. Existing methods suffer from performance degradation caused by the distribution shift of label…

In this paper, we study the problem of recognizing compositional attribute-object concepts within the zero-shot learning (ZSL) framework. We propose an episode-based cross-attention (EpiCA) network which combines merits of cross-attention…

This article introduces a novel approach to the classification of categorical time series under the supervised learning paradigm. To construct meaningful features for categorical time series classification, we consider two relevant…

In this paper, we propose a machine learning model for sparse pairwise comparison matrices (PCMs), combining classical PCM approaches with graph-based learning techniques. Numerical results are provided to demonstrate the effectiveness and…

Spatial coupling was proved to improve the belief-propagation (BP) performance up to the maximum-a-posteriori (MAP) performance. This paper addresses an extended class of spatially coupled (SC) systems. A potential function is derived for…

With the advent of vision-language models (e.g., CLIP) in zero- and few-shot settings, CLIP has been widely applied to zero-shot anomaly detection (ZSAD) in recent research, where the rare classes are essential and expected in many…

Zero-shot learning (ZSL) can be formulated as a cross-domain matching problem: after being projected into a joint embedding space, a visual sample will match against all candidate class-level semantic descriptions and be assigned to the…

General purpose semantic segmentation relies on a backbone CNN network to extract discriminative features that help classify each image pixel into a 'seen' object class (ie., the object classes available during training) or a background…

In this paper, we propose a sequence construction framework that extends prime-length Bj\"orck sequences, a class of Constant Amplitude Zero Autocorrelation (CAZAC) sequences, to arbitrary lengths using Goldbach's conjecture for even and…

We consider spatially coupled code ensembles. A particular instance are convolutional LDPC ensembles. It was recently shown that, for transmission over the memoryless binary erasure channel, this coupling increases the belief propagation…