Related papers: Omni Aggregation Networks for Lightweight Image Su…

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Convolutional neural networks are the most successful models in single image super-resolution. Deeper networks, residual connections, and attention mechanisms have further improved their performance. However, these strategies often improve…

The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…

The architecture of deep convolutional networks (CNNs) has evolved for years, becoming more accurate and faster. However, it is still challenging to design reasonable network structures that aim at obtaining the best accuracy under a…

We present a novel architecture for dense correspondence. The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggregation. However, they generally aggregate one or the other…

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

Retinal Optical Coherence Tomography Angiography (OCTA) with high-resolution is important for the quantification and analysis of retinal vasculature. However, the resolution of OCTA images is inversely proportional to the field of view at…

Deep learning has been successfully applied to the single-image super-resolution (SISR) task with great performance in recent years. However, most convolutional neural network based SR models require heavy computation, which limit their…

The visuomotor policy can easily overfit to its training datasets, such as fixed camera positions and backgrounds. This overfitting makes the policy perform well in the in-distribution scenarios but underperform in the out-of-distribution…

The Swin Transformer image super-resolution (SR) reconstruction network primarily depends on the long-range relationship of the window and shifted window attention to explore features. However, this approach focuses only on global features,…

The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual quality of videos, by simultaneously performing video frame interpolation (VFI) and video super-resolution (VSR). However, facing the challenge of the additional…

Most recent video super-resolution (SR) methods either adopt an iterative manner to deal with low-resolution (LR) frames from a temporally sliding window, or leverage the previously estimated SR output to help reconstruct the current frame…

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision transformers demonstrate promising performance, they often…

Super-resolution (SR) has achieved great success due to the development of deep convolutional neural networks (CNNs). However, as the depth and width of the networks increase, CNN-based SR methods have been faced with the challenge of…

Learning subtle representation about object parts plays a vital role in fine-grained visual recognition (FGVR) field. The vision transformer (ViT) achieves promising results on computer vision due to its attention mechanism. Nonetheless,…

A few lightweight convolutional neural network (CNN) models have been recently designed for remote sensing object detection (RSOD). However, most of them simply replace vanilla convolutions with stacked separable convolutions, which may not…

Although vision Transformers have achieved excellent performance as backbone models in many vision tasks, most of them intend to capture global relations of all tokens in an image or a window, which disrupts the inherent spatial and local…

Although many recent works have made advancements in the image restoration (IR) field, they often suffer from an excessive number of parameters. Another issue is that most Transformer-based IR methods focus only on either local or global…

It has become a standard practice to use the convolutional networks (ConvNet) with RELU non-linearity in image restoration and super-resolution (SR). Although the universal approximation theorem states that a multi-layer neural network can…

Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…