Related papers: LSAS: Lightweight Sub-attention Strategy for Allev…

Attention-based graph neural networks have made great progress in feature matching learning. However, insight of how attention mechanism works for feature matching is lacked in the literature. In this paper, we rethink cross- and…

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…

Convolution neural networks (CNNs) based methods have dominated the low-light image enhancement tasks due to their outstanding performance. However, the convolution operation is based on a local sliding window mechanism, which is difficult…

The accurate detection of lesion attributes is meaningful for both the computeraid diagnosis system and dermatologists decisions. However, unlike lesion segmentation and melenoma classification, there are few deep learning methods and…

Deep spiking neural networks (SNNs) have emerged as a potential alternative to traditional deep learning frameworks, due to their promise to provide increased compute efficiency on event-driven neuromorphic hardware. However, to perform…

Advanced Driver Assistance Systems (ADAS) based on deep neural networks (DNNs) are widely used in autonomous vehicles for critical perception tasks such as object detection, semantic segmentation, and lane recognition. However, these…

A modern deep neural network (DNN) for image classification tasks typically consists of two parts: a backbone for feature extraction, and a head for feature encoding and class predication. We observe that the head structures of mainstream…

CNNs and Self attention have achieved great success in multimedia applications for dynamic association learning of self-attention and convolution in image restoration. However, CNNs have at least two shortcomings: 1) limited receptive…

Transformers are becoming the mainstream solutions for various tasks like NLP and Computer vision. Despite their success, the high complexity of the attention mechanism hinders them from being applied to latency-sensitive tasks. Tremendous…

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

Fine-grained visual classification is a challenging task that recognizes the sub-classes belonging to the same meta-class. Large inter-class similarity and intra-class variance is the main challenge of this task. Most exiting methods try to…

Label noise poses a serious threat to deep neural networks (DNNs). Employing robust loss functions which reconcile fitting ability with robustness is a simple but effective strategy to handle this problem. However, the widely-used static…

In image denoising, deep convolutional neural networks (CNNs) can obtain favorable performance on removing spatially invariant noise. However, many of these networks cannot perform well on removing the real noise (i.e. spatially variant…

Deep learning has emerged as a transformative tool in healthcare, offering significant advancements in dental diagnostics by analyzing complex imaging data. This paper presents an enhanced ResNet50 architecture, integrated with the SimAM…

Digital whole slide images (WSIs) are generally captured at microscopic resolution and encompass extensive spatial data. Directly feeding these images to deep learning models is computationally intractable due to memory constraints, while…

Retinal vessel segmentation is critical for the early diagnosis of vision-threatening and systemic diseases, especially in real-world clinical settings with limited computational resources. Although significant improvements have been made…

While significant advances in deep learning has resulted in state-of-the-art performance across a large number of complex visual perception tasks, the widespread deployment of deep neural networks for TinyML applications involving…

Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such noisy data, several algorithms have been proposed. A…

Lesion segmentation on nasal endoscopic images is challenging due to its complex lesion features. Fully-supervised deep learning methods achieve promising performance with pixel-level annotations but impose a significant annotation burden…

One of the most popular paradigms of applying large pre-trained NLP models such as BERT is to fine-tune it on a smaller dataset. However, one challenge remains as the fine-tuned model often overfits on smaller datasets. A symptom of this…