Related papers: FFT-based Dynamic Token Mixer for Vision

A mixed precision Fast Fourier transform (FFT) implementation is presented. The procedure uses per-block microscaling (MX), a global power-of-two prescale, and prequantized low bit twiddles. We evaluate forward and round-trip FFT fidelity…

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…

Nearly every recent image synthesis approach, including diffusion, masked-token prediction, and next-token prediction, uses a Transformer network architecture. Despite this common backbone, there has been no direct, compute controlled…

Recent works in dataset distillation seek to minimize training expenses by generating a condensed synthetic dataset that encapsulates the information present in a larger real dataset. These approaches ultimately aim to attain test accuracy…

While significant progress has been achieved in multimodal facial generation using semantic masks and textual descriptions, conventional feature fusion approaches often fail to enable effective cross-modal interactions, thereby leading to…

Video object detection is a fundamental yet challenging task in computer vision. One practical solution is to take advantage of temporal information from the video and apply feature aggregation to enhance the object features in each frame.…

Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate both, they apply the two operators simultaneously at the…

In recent years, many video tasks have achieved breakthroughs by utilizing the vision transformer and establishing spatial-temporal decoupling for feature extraction. Although multi-view 3D reconstruction also faces multiple images as…

Transformer-based architectures are the model of choice for natural language understanding, but they come at a significant cost, as they have quadratic complexity in the input length, require a lot of training data, and can be difficult to…

Recent advancements in learned image compression (LIC) methods have demonstrated superior performance over traditional hand-crafted codecs. These learning-based methods often employ convolutional neural networks (CNNs) or Transformer-based…

Local feature matching remains a challenging task, primarily due to difficulties in matching sparse keypoints and low-texture regions. The key to solving this problem lies in effectively and accurately integrating global and local…

Lightweight and efficiency are critical drivers for the practical application of image super-resolution (SR) algorithms. We propose a simple and effective approach, ShuffleMixer, for lightweight image super-resolution that explores large…

Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory…

Multi-focus is a technique of focusing on different aspects of a particular object or scene. Wireless Visual Sensor Networks (WVSN) use multi-focus image fusion, which combines two or more images to create a more accurate output image that…

This paper presents a novel neural network architecture featuring automatic fixation point selection, designed to efficiently address complex tasks with reduced network size and computational overhead. The proposed model consists of: a…

Vision Transformers have demonstrated exceptional performance across various computer vision tasks, yet their quadratic computational complexity concerning token length remains a significant challenge. To address this, token reduction…

Vision transformers have gained popularity recently, leading to the development of new vision backbones with improved features and consistent performance gains. However, these advancements are not solely attributable to novel feature…

Semantic segmentation is crucial for medical image analysis, enabling precise disease diagnosis and treatment planning. However, many advanced models employ complex architectures, limiting their use in resource-constrained clinical…

Recently, deep learning based facial landmark detection (FLD) methods have achieved considerable success. However, in challenging scenarios such as large pose variations, illumination changes, and facial expression variations, they still…

The application of machine learning to image and video data often yields a high dimensional feature space. Effective feature selection techniques identify a discriminant feature subspace that lowers computational and modeling costs with…