Related papers: Pyramid Attention Networks for Image Restoration

Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks. Self-attention updates the feature at each position by computing a weighted sum of features using…

The aim of image restoration is to recover high-quality images from distorted ones. However, current methods usually focus on a single task (\emph{e.g.}, denoising, deblurring or super-resolution) which cannot address the needs of…

Unsupervised anomaly detection plays a pivotal role in industrial defect inspection and medical image analysis, with most methods relying on the reconstruction framework. However, these methods may suffer from over-generalization, enabling…

This work aims at designing a lightweight convolutional neural network for image super resolution (SR). With simplicity bare in mind, we construct a pretty concise and effective network with a newly proposed pixel attention scheme. Pixel…

Image retrieval aims to identify visually similar images within a database using a given query image. Traditional methods typically employ both global and local features extracted from images for matching, and may also apply re-ranking…

We propose Diverse Restormer (DART), a novel image restoration method that effectively integrates information from various sources (long sequences, local and global regions, feature dimensions, and positional dimensions) to address…

The Transformer architecture has witnessed a rapid development in recent years, outperforming the CNN architectures in many computer vision tasks, as exemplified by the Vision Transformers (ViT) for image classification. However, existing…

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…

Recognizing and localizing events in videos is a fundamental task for video understanding. Since events may occur in auditory and visual modalities, multimodal detailed perception is essential for complete scene comprehension. Most previous…

Articulated human pose estimation is a fundamental yet challenging task in computer vision. The difficulty is particularly pronounced in scale variations of human body parts when camera view changes or severe foreshortening happens.…

Recent deep learning based image inpainting methods which utilize contextual information and two-stage architecture have exhibited remarkable performance. However, the two-stage architecture is time-consuming, the contextual information…

CNNs, initially inspired by human vision, differ in a key way: they sample uniformly, rather than with highest density in a focal point. For very large images, this makes training untenable, as the memory and computation required for…

For Convolutional Neural Network-based object detection, there is a typical dilemma: the spatial information is well kept in the shallow layers which unfortunately do not have enough semantic information, while the deep layers have a high…

Over the last few years, deep learning based approaches have achieved outstanding improvements in natural image matting. Many of these methods can generate visually plausible alpha estimations, but typically yield blurry structures or…

Recently, numerous studies have been conducted on supervised learning-based image denoising methods. However, these methods rely on large-scale noisy-clean image pairs, which are difficult to obtain in practice. Denoising methods with…

Monocular depth estimation is an essential task for scene understanding. The underlying structure of objects and stuff in a complex scene is critical to recovering accurate and visually-pleasing depth maps. Global structure conveys scene…

Medical image processing tasks such as segmentation often require capturing non-local information. As organs, bones, and tissues share common characteristics such as intensity, shape, and texture, the contextual information plays a critical…

Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks. Yet, its underlying working principles remain somewhat elusive. What is its essence? Are…

Feature pyramids have been proven powerful in image understanding tasks that require multi-scale features. State-of-the-art methods for multi-scale feature learning focus on performing feature interactions across space and scales using…

This paper proposes a Rotation-equivariant Attention Feature Fusion Pyramid Networks for Aerial Object Detection named ReAFFPN. ReAFFPN aims at improving the effect of rotation-equivariant features fusion between adjacent layers which…