Related papers: Shuffle Transformer: Rethinking Spatial Shuffle fo…

Recently Transformer has shown good performance in several vision tasks due to its powerful modeling capabilities. To reduce the quadratic complexity caused by the attention, some outstanding work restricts attention to local regions or…

Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image…

Vision transformers have become popular as a possible substitute to convolutional neural networks (CNNs) for a variety of computer vision applications. These transformers, with their ability to focus on global relationships in images, offer…

The past year has witnessed the rapid development of applying the Transformer module to vision problems. While some researchers have demonstrated that Transformer-based models enjoy a favorable ability of fitting data, there are still…

Shadow detection is a fundamental and challenging task in many computer vision applications. Intuitively, most shadows come from the occlusion of light by the object itself, resulting in the object and its shadow being contiguous (referred…

To address the high resolution of image pixels, the Swin Transformer introduces window attention. This mechanism divides an image into non-overlapping windows and restricts attention computation to within each window, significantly…

Transformers have revolutionized computer vision and natural language processing, but their high computational complexity limits their application in high-resolution image processing and long-context analysis. This paper introduces…

Image Classification is a fundamental task in the field of computer vision that frequently serves as a benchmark for gauging advancements in Computer Vision. Over the past few years, significant progress has been made in image…

Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical…

Following the success in language domain, the self-attention mechanism (transformer) is adopted in the vision domain and achieving great success recently. Additionally, as another stream, multi-layer perceptron (MLP) is also explored in the…

Transformers have emerged as viable alternatives to convolutional neural networks owing to their ability to learn non-local region relationships in the spatial domain. The self-attention mechanism of the transformer enables transformers to…

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent…

Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only utilize a limited spatial range of input information through…

Until quite recently, the backbone of nearly every state-of-the-art computer vision model has been the 2D convolution. At its core, a 2D convolution simultaneously mixes information across both the spatial and channel dimensions of a…

Vision transformers have gained significant attention and achieved state-of-the-art performance in various computer vision tasks, including image classification, instance segmentation, and object detection. However, challenges remain in…

Over the past decade, deep learning research has been accelerated by increasingly powerful hardware, which facilitated rapid growth in the model complexity and the amount of data ingested. This is becoming unsustainable and therefore…

While scale-invariant modeling has substantially boosted the performance of visual recognition tasks, it remains largely under-explored in deep networks based image restoration. Naively applying those scale-invariant techniques (e.g.…

Interactive image segmentation aims to segment the target from the background with the manual guidance, which takes as input multimodal data such as images, clicks, scribbles, and bounding boxes. Recently, vision transformers have achieved…

This paper is on video recognition using Transformers. Very recent attempts in this area have demonstrated promising results in terms of recognition accuracy, yet they have been also shown to induce, in many cases, significant computational…

Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the design of hand-crafted windows, which is data-agnostic,…