Related papers: Efficient Star Distillation Attention Network for …

Self-attention mechanisms are commonly included in a convolutional neural networks to achieve an improved efficiency performance balance. However, adding self-attention mechanisms adds additional hyperparameters to tune for the application…

Deep learning-based single-image super-resolution (SISR) technology focuses on enhancing low-resolution (LR) images into high-resolution (HR) ones. Although significant progress has been made, challenges remain in computational complexity…

Single-image super-resolution (SISR) typically focuses on restoring various degraded low-resolution (LR) images to a single high-resolution (HR) image. However, during SISR tasks, it is often challenging for models to simultaneously…

Spiking Neural Networks (SNNs) are biologically realistic and practically promising in low-power computation because of their event-driven mechanism. Usually, the training of SNNs suffers accuracy loss on various tasks, yielding an inferior…

Distilling pretrained softmax attention Transformers into more efficient hybrid architectures that interleave softmax and linear attention layers is a promising approach for improving the inference efficiency of LLMs without requiring…

Large-scale models (LSMs) can be an effective framework for semantic representation and understanding, thereby providing a suitable tool for designing semantic communication (SC) systems. However, their direct deployment is often hindered…

4D radar super-resolution, which aims to reconstruct sparse and noisy point clouds into dense and geometrically consistent representations, is a foundational problem in autonomous perception. However, existing methods often suffer from high…

The Segment Anything Model (SAM) has advanced interactive segmentation but is limited by the high computational cost on high-resolution images. This requires downsampling to meet GPU constraints, sacrificing the fine-grained details needed…

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…

Light field (LF) images can be used to improve the performance of image super-resolution (SR) because both angular and spatial information is available. It is challenging to incorporate distinctive information from different views for LF…

Image restoration is a long-standing task that seeks to recover the latent sharp image from its deteriorated counterpart. Due to the robust capacity of self-attention to capture long-range dependencies, transformer-based methods or some…

State-of-the-art frameworks in self-supervised learning have recently shown that fully utilizing transformer-based models can lead to performance boost compared to conventional CNN models. Striving to maximize the mutual information of two…

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…

Image restoration is a challenging ill-posed problem which estimates latent sharp image from its degraded counterpart. Although the existing methods have achieved promising performance by designing novelty architecture of module, they…

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…

Recently, transformer-based methods have demonstrated impressive results in various vision tasks, including image super-resolution (SR), by exploiting the self-attention (SA) for feature extraction. However, the computation of SA in most…

This technical note describes the design and modular implementation of a one-dimensional convolutional neural network (1D CNN) adapted from residual networks (ResNet), developed for photometric regression tasks with an emphasis on low star…

The rapid development of deep learning provides a better solution for the end-to-end reconstruction of hyperspectral image (HSI). However, existing learning-based methods have two major defects. Firstly, networks with self-attention usually…

Surface defect detection is one of the most essential processes for industrial quality inspection. Deep learning-based surface defect detection methods have shown great potential. However, the well-performed models usually require large…

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…