Related papers: Self-Calibrated Efficient Transformer for Lightwei…
While recent Transformer-based approaches have shown impressive performances on event-based object detection tasks, their high computational costs still diminish the low power consumption advantage of event cameras. Image-based works…
Purpose: To develop a model-based deep neural network for high-quality image reconstruction of undersampled multi-coil chemical exchange saturation transfer (CEST) data. Theory and Methods: Inspired by the variational network, the CEST…
Single image super-resolution (SISR) is an image processing task which obtains high-resolution (HR) image from a low-resolution (LR) image. Recently, due to the capability in feature extraction, a series of deep learning methods have…
Convolutional neural network (CNN) based image enhancement methods such as super-resolution and detail enhancement have achieved remarkable performances. However, amounts of operations including convolution and parameters within the…
This paper is concerned with self-supervised learning for small models. The problem is motivated by our empirical studies that while the widely used contrastive self-supervised learning method has shown great progress on large model…
Recently, Convolutional Neural Networks (CNNs) have been successfully adopted to solve the ill-posed single image super-resolution (SISR) problem. A commonly used strategy to boost the performance of CNN-based SISR models is deploying very…
We propose a semi-supervised network for wide-angle portraits correction. Wide-angle images often suffer from skew and distortion affected by perspective distortion, especially noticeable at the face regions. Previous deep learning based…
Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each…
In remote sensing images, complex backgrounds, weak object signals, and small object scales make accurate detection particularly challenging, especially under low-quality imaging conditions. A common strategy is to integrate single-image…
Although several image super-resolution solutions exist, they still face many challenges. CNN-based algorithms, despite the reduction in computational complexity, still need to improve their accuracy. While Transformer-based algorithms have…
Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…
In this paper, we propose a simple while effective unsupervised deep feature transfer algorithm for low resolution image classification. No fine-tuning on convenet filters is required in our method. We use pre-trained convenet to extract…
Deep learning models are increasingly utilized on resource-constrained edge devices for real-time data analytics. Recently, Vision Transformer and their variants have shown exceptional performance in various computer vision tasks. However,…
Recently, Transformer-based architectures have been explored for speaker embedding extraction. Although the Transformer employs the self-attention mechanism to efficiently model the global interaction between token embeddings, it is…
Currently, most deep learning methods cannot solve the problem of scarcity of industrial product defect samples and significant differences in characteristics. This paper proposes an unsupervised defect detection algorithm based on a…
Accurate medical image segmentation is of utmost importance for enabling automated clinical decision procedures. However, prevailing supervised deep learning approaches for medical image segmentation encounter significant challenges due to…
Deep learning based methods have recently pushed the state-of-the-art on the problem of Single Image Super-Resolution (SISR). In this work, we revisit the more traditional interpolation-based methods, that were popular before, now with the…
Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so…
In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device. However, this pipeline…
Transformer-based Super-Resolution (SR) methods have demonstrated superior performance compared to convolutional neural network (CNN)-based SR approaches due to their capability to capture long-range dependencies. However, their high…