Related papers: Joint Model and Data Driven Receiver Design for Da…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking.…

This paper presents a data-aided channel estimator that reduces the channel estimation error of the conventional linear minimum-mean-squared-error (LMMSE) method for multiple-input multiple-output communication systems. The basic idea is to…

As the scale and complexity of integrated circuits continue to increase, traditional modeling methods are struggling to address the nonlinear challenges in radio frequency (RF) chips. Deep learning has been increasingly applied to RF device…

In modern parametric model training, full-batch gradient descent (and its variants) suffers due to progressively stronger biasing towards the exact realization of training data; this drives the systematic ``generalization gap'', where the…

We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale training, and their variants are aiming at preparing…

Achieving state-of-the-art results in face verification systems typically hinges on the availability of labeled face training data, a resource that often proves challenging to acquire in substantial quantities. In this research endeavor, we…

Infrared small target detection (IRSTD) plays a pivotal role in a broad spectrum of mission-critical applications, including maritime surveillance, military search and rescue, early warning systems, and precision-guided strikes, all of…

In this work, we propose a data-driven scheme to initialize the parameters of a deep neural network. This is in contrast to traditional approaches which randomly initialize parameters by sampling from transformed standard distributions.…

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

A unified self-supervised and supervised deep learning framework for PET image reconstruction is presented, including deep-learned filtered backprojection (DL-FBP) for sinograms, deep-learned backproject then filter (DL-BPF) for…

The superimposed pilot transmission scheme offers substantial potential for improving spectral efficiency in MIMO-OFDM systems, but it presents significant challenges for receiver design due to pilot contamination and data interference. To…

The paper studies the scenario of wireless multicast with a single transmitter and a relay that deliver scalable source symbols to the receivers in a decode-and-forward (DF) fashion. With the end-to-end mean square error distortion (EED) as…

It is well known that matched filtering and sampling (MFS) demodulation together with minimum Euclidean distance (MD) detection constitute the optimal receiver for the additive white Gaussian noise channel. However, for a general nonlinear…

Deep neural networks have been widely used in communication signal recognition and achieved remarkable performance, but this superiority typically depends on using massive examples for supervised learning, whereas training a deep neural…

Deep Neural Networks (DNNs) often rely on very large datasets for training. Given the large size of such datasets, it is conceivable that they contain certain samples that either do not contribute or negatively impact the DNN's…

Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incurs substantial memory overhead. Delta compression addresses this by retaining a single…

Recent years have witnessed growing interest in the application of deep neural networks (DNNs) for receiver design, which can potentially be applied in complex environments without relying on knowledge of the channel model. However, the…

Federated Learning is an algorithm suited for training models on decentralized data, but the requirement of a central "server" node is a bottleneck. In this document, we first introduce the notion of Decentralized Federated Learning (DFL).…

Recent semi-supervised learning methods use pseudo supervision as core idea, especially self-training methods that generate pseudo labels. However, pseudo labels are unreliable. Self-training methods usually rely on single model prediction…