Related papers: CATs++: Boosting Cost Aggregation with Convolution…

In the field of single image super-resolution (SISR), transformer-based models, have demonstrated significant advancements. However, the potential and efficiency of these models in applied fields such as real-world image super-resolution…

Recent years have witnessed the success of deep networks in compressed sensing (CS), which allows for a significant reduction in sampling cost and has gained growing attention since its inception. In this paper, we propose a new practical…

Point cloud recognition is an essential task in industrial robotics and autonomous driving. Recently, several point cloud processing models have achieved state-of-the-art performances. However, these methods lack rotation robustness, and…

The recent demand for customized image generation raises a need for techniques that effectively extract the common concept from small sets of images. Existing methods typically rely on additional guidance, such as text prompts or spatial…

Traditional studies emphasize the significance of context information in improving matting performance. Consequently, deep learning-based matting methods delve into designing pooling or affinity-based context aggregation modules to achieve…

Convolutional neural networks (CNNs) require a large number of multiply-accumulate (MAC) operations. To meet real-time constraints, they often need to be executed on specialized accelerators composed of an on-chip memory and a processing…

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Hybrid CNN-Transformer architectures achieve strong results in image super-resolution, but scaling attention windows or convolution kernels significantly increases computational cost, limiting deployment on resource-constrained devices. We…

Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. However, pure Transformer architectures often require a large…

State-of-the-art image inpainting approaches can suffer from generating distorted structures and blurry textures in high-resolution images (e.g., 512x512). The challenges mainly drive from (1) image content reasoning from distant contexts,…

The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, the field has increasingly prioritized marginal performance gains on a…

As convolutional neural networks (CNNs) enable state-of-the-art computer vision applications, their high energy consumption has emerged as a key impediment to their deployment on embedded and mobile devices. Towards efficient image…

Graph Convolutional Networks (GCNs) are widely used to improve recommendation accuracy and performance by effectively learning the representations of user and item nodes. However, two major challenges remain: (1) the lack of further…

Convolutional neural networks (CNNs) are ubiquitous in computer vision, with a myriad of effective and efficient variations. Recently, Transformers -- originally introduced in natural language processing -- have been increasingly adopted in…

Transformers achieve strong performance across diverse domains but implicitly assume Euclidean geometry in their attention mechanisms, limiting their effectiveness on data with non-Euclidean structure. While recent extensions to hyperbolic…

With the development of technology rapidly, applications of convolutional neural networks have improved the convenience of our life. However, in image classification field, it has been found that when some perturbations are added to images,…

Cooperative perception significantly enhances scene understanding by integrating complementary information from diverse agents. However, existing research often overlooks critical challenges inherent in real-world multi-source data…

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate…

Given the rapid development of 3D scanners, point clouds are becoming popular in AI-driven machines. However, point cloud data is inherently sparse and irregular, causing significant difficulties for machine perception. In this work, we…

Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes local interactions. This…