Related papers: Advanced Equalization in 112 Gb/s Upstream PON Usi…

A standard practice in developing image recognition models is to train a model on a specific image resolution and then deploy it. However, in real-world inference, models often encounter images different from the training sets in resolution…

To build light-weight network, we propose a new normalization, Fine-grained Batch Normalization (FBN). Different from Batch Normalization (BN), which normalizes the final summation of the weighted inputs, FBN normalizes the intermediate…

Burst-mode DSP based on 10ns preamble is proposed for upstream reception of 200G coherent TDM-PON. The 128-symbol tone preamble is used for SOP, frequency offset, and sampling phase estimation, while the 192-symbol CAZAC preamble is used…

Accurate sea ice mapping is essential for safe maritime navigation in polar regions, where rapidly changing ice conditions require timely and reliable information. While Sentinel-1 Synthetic Aperture Radar (SAR) provides high-resolution,…

Convolutional neural networks (CNNs) are currently state-of-the-art for various classification tasks, but are computationally expensive. Propagating through the convolutional layers is very slow, as each kernel in each layer must…

Fully convolutional recurrent neural networks (FCRNs) have shown state-of-the-art performance in single-channel speech enhancement. However, the number of parameters and the FLOPs/second of the original FCRN are restrictively high. A…

This paper proposes to use Fast Fourier Transformation-based U-Net (a refined fully convolutional networks) and perform image convolution in neural networks. Leveraging the Fast Fourier Transformation, it reduces the image convolution costs…

We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet. Furthermore, it uses less parameters than previous networks, making it…

This work evaluates State-of-the-Art convolution algorithms for CPU-based CNN inference. Although most prior studies focus on GPUs or NPUs, CPU implementations remain comparatively under-optimized. Our first contribution is to provide fair…

Accurate and adaptive network throughput prediction is essential for latency-sensitive and bandwidth-intensive applications in 5G and emerging 6G networks. However, most existing methods rely on centralized training with uniformly collected…

Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising. However, these methods mostly learn a specific model for each noise level, and require multiple models for…

This paper describes the limiting behavior of linear and decision feedback equalizers (DFEs) in single/multiple antenna systems employing real/complex-valued modulation alphabets. The wideband frequency selective channel is modeled using a…

Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic studies on how an…

Binaural speech enhancement faces a severe trade-off challenge, where state-of-the-art performance is achieved by computationally intensive architectures, while lightweight solutions often come at the cost of significant performance…

Convolution Neural Networks (CNN) have been extremely successful in solving intensive computer vision tasks. The convolutional filters used in CNNs have played a major role in this success, by extracting useful features from the inputs.…

Structured CNN designed using the prior information of problems potentially improves efficiency over conventional CNNs in various tasks in solving PDEs and inverse problems in signal processing. This paper introduces BNet2, a simplified…

We present an approach to accelerating a wide variety of image processing operators. Our approach uses a fully-convolutional network that is trained on input-output pairs that demonstrate the operator's action. After training, the original…

The new generation of domain-specific AI accelerators is characterized by rapidly increasing demands for bulk data transfers, as opposed to small, latency-critical cache line transfers typical of traditional cache-coherent systems. In this…

Recent findings indicate that over-parametrization, while crucial for successfully training deep neural networks, also introduces large amounts of redundancy. Tensor methods have the potential to efficiently parametrize over-complete…

Noise in image sensors led to the development of a whole range of denoising filters. A noisy image can become hard to recognize and often require several types of post-processing compensation circuits. This paper proposes an adaptive…