Related papers: Exploring Frequency-Inspired Optimization in Trans…

Post-training quantization (PTQ) efficiently compresses vision models, but unfortunately, it accompanies a certain degree of accuracy degradation. Reconstruction methods aim to enhance model performance by narrowing the gap between the…

Transformer-based architectures like BERT have achieved great success in a wide range of Natural Language tasks. Despite their decent performance, the models still have numerous parameters and high computational complexity, impeding their…

Transformers-based methods have achieved significant performance in image deraining as they can model the non-local information which is vital for high-quality image reconstruction. In this paper, we find that most existing Transformers…

Visual generation quality has been greatly promoted with the rapid advances in diffusion transformers (DiTs), which is attributed to the scaling of model size and complexity. However, these attributions also hinder the practical deployment…

Graph Transformer is gaining increasing attention in the field of machine learning and has demonstrated state-of-the-art performance on benchmarks for graph representation learning. However, as current implementations of Graph Transformer…

This paper investigates automatic piano transcription based on computationally-efficient yet high-performant variants of the Transformer that can capture longer-term dependency over the whole musical piece. Recently, transformer-based…

Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image…

Parameterized quantum circuits (PQCs) have recently emerged as promising components for enhancing the expressibility of neural architectures. In this work, we introduce QFFN-BERT, a hybrid quantum-classical transformer where the feedforward…

Spectral analysis provides one of the most effective paradigms for information-preserving dimensionality reduction, as simple descriptions of naturally occurring signals are often obtained via few terms of periodic basis functions. In this…

Post-Training Quantization (PTQ) is pivotal for deploying large language models (LLMs) within resource-limited settings by significantly reducing resource demands. However, existing PTQ strategies underperform at low bit levels < 3 bits due…

Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment, which allows advanced SR models to enjoy compact low-bit parameters and efficient integer/bitwise constructions for storage…

Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task.…

We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical…

Time-frequency representations, such as the short-time Fourier transform (STFT), are fundamental tools for analyzing non-stationary signals. However, their ability to achieve sharp localization in both time and frequency is inherently…

Although numerous solutions have been proposed for image super-resolution, they are usually incompatible with low-power devices with many computational and memory constraints. In this paper, we address this problem by proposing a simple yet…

Previous works have shown that reducing parameter overhead and computations for transformer-based single image super-resolution (SISR) models (e.g., SwinIR) usually leads to a reduction of performance. In this paper, we present GRFormer, an…

High-quality remote sensing (RS) image acquisition is fundamentally constrained by physical limitations. While Multi-Frame Super-Resolution (MFSR) and Pansharpening address this by exploiting complementary information, they are typically…

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challenging and also rarely…

Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent…

Discrete Wavelet Transform (DWT) has been widely explored to enhance the performance of image superresolution (SR). Despite some DWT-based methods improving SR by capturing fine-grained frequency signals, most existing approaches neglect…