Related papers: 10K is Enough: An Ultra-Lightweight Binarized Netw…

Hyperspectral image (HSI) denoising is a crucial preprocessing step for subsequent tasks. The clean HSI usually reside in a low-dimensional subspace, which can be captured by low-rank and sparse representation, known as the physical prior…

Deploying convolutional neural networks (CNNs) for embedded applications presents many challenges in balancing resource-efficiency and task-related accuracy. These two aspects have been well-researched in the field of CNN compression. In…

Accurate segmentation of anatomical structures and abnormalities in medical images is crucial for computer-aided diagnosis and analysis. While deep learning techniques excel at this task, their computational demands pose challenges.…

IRSTD (InfraRed Small Target Detection) detects small targets in infrared blurry backgrounds and is essential for various applications. The detection task is challenging due to the small size of the targets and their sparse distribution in…

Learning compact binary codes for image retrieval problem using deep neural networks has recently attracted increasing attention. However, training deep hashing networks is challenging due to the binary constraints on the hash codes. In…

Traditional semantic segmentation tasks require a large number of labels and are difficult to identify unlearned categories. Few-shot semantic segmentation (FSS) aims to use limited labeled support images to identify the segmentation of new…

1 bit deep neural networks (DNNs), of which both the activations and weights are binarized , are attracting more and more attention due to their high computational efficiency and low memory requirement . However, the drawback of large…

Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate…

Recently, many Convolution Neural Networks (CNN) have been successfully employed in bitemporal SAR image change detection. However, most of the existing networks are too heavy and occupy a large volume of memory for storage and calculation.…

Surgical instrument segmentation is extremely important for computer-assisted surgery. Different from common object segmentation, it is more challenging due to the large illumination and scale variation caused by the special surgical…

Deep neural networks are state-of-the-art models for understanding the content of images, video and raw input data. However, implementing a deep neural network in embedded systems is a challenging task, because a typical deep neural…

Deep convolutional neural networks (DCNNs) have substantially advanced object detection capabilities, particularly in remote sensing imagery. However, challenges persist, especially in detecting small objects where the high resolution of…

Convolutional neural networks (CNNs) are effective for hyperspectral image (HSI) classification, but their 3D convolutional structures introduce high computational costs and limited generalization in few-shot scenarios. Domain shifts caused…

In this paper, we propose to train a network with binary weights and low-bitwidth activations, designed especially for mobile devices with limited power consumption. Most previous works on quantizing CNNs uncritically assume the same…

Reduced-precision arithmetic improves the size, cost, power and performance of neural networks in digital logic. In convolutional neural networks, the use of 1b weights can achieve state-of-the-art error rates while eliminating…

Although Convolutional Neural Networks (CNNs) achieve effectiveness in various computer vision tasks, the significant requirement of storage of such networks hinders the deployment on computationally limited devices. In this paper, we…

Recent work has shown that fast, compact low-bitwidth neural networks can be surprisingly accurate. These networks use homogeneous binarization: all parameters in each layer or (more commonly) the whole model have the same low bitwidth…

Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains…

Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities. The most recent deep learning based SISR methods focus…

The rapid expansion of Internet of Things (IoT) deployments has enlarged the attack surface of modern digital infrastructure while exposing a key security mismatch: many intrusion detection systems (IDSs) remain too computationally…