Related papers: Discrete Cosine Transform Based Decorrelated Atten…

Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language…

Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is a fundamental problem in 3D perception. Compared with the customized sparse convolution, the attention mechanism in Transformers is more appropriate…

Designing an effective channel attention mechanism implores one to find a lossy-compression method allowing for optimal feature representation. Despite recent progress in the area, it remains an open problem. FcaNet, the current…

Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers.…

Transformer has been very successful in various computer vision tasks and understanding the working mechanism of transformer is important. As touchstones, weakly-supervised semantic segmentation (WSSS) and class activation map (CAM) are…

The feature learning methods based on convolutional neural network (CNN) have successfully produced tremendous achievements in image classification tasks. However, the inherent noise and some other factors may weaken the effectiveness of…

Fast MRI aims to reconstruct a high fidelity image from partially observed measurements. Exuberant development in fast MRI using deep learning has been witnessed recently. Meanwhile, novel deep learning paradigms, e.g., Transformer based…

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by the global self-attention, various methods constrain the range of attention within a local region to…

Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for…

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers…

Large vision-and-language models (LVLMs) have traditionally integrated visual and textual tokens by concatenating them into a single homogeneous input for large language models (LLMs), thereby maximally preserving the pre-trained language…

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Compressing the sign information of discrete cosine transform (DCT) coefficients is an intractable problem in image coding schemes due to the equiprobable characteristics of the signs. To overcome this difficulty, we propose an efficient…

Spiking Neural Networks (SNNs) offer a promising alternative to traditional deep learning frameworks, since they provide higher computational efficiency due to event-driven information processing. SNNs distribute the analog values of pixel…

Due to the confined focal length of optical sensors, focusing all objects in a scene with a single sensor is a difficult task. To handle such a situation, image fusion methods are used in multi-focus environment. Discrete Cosine Transform…

Recently, transformer has achieved remarkable performance on a variety of computer vision applications. Compared with mainstream convolutional neural networks, vision transformers are often of sophisticated architectures for extracting…

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Single Image Super-Resolution (SISR) reconstructs high-resolution images from low-resolution inputs, enhancing image details. While Vision Transformer (ViT)-based models improve SISR by capturing long-range dependencies, they suffer from…

Achieving highly accurate and real-time 3D occupancy prediction from cameras is a critical requirement for the safe and practical deployment of autonomous vehicles. While this shift to sparse 3D representations solves the encoding…

Monocular depth estimation is a central problem in computer vision with applications in robotics, AR, and autonomous driving, yet the self-attention mechanisms that drive modern Transformer architectures remain opaque. We introduce…