English
Related papers

Related papers: Fast-FNet: Accelerating Transformer Encoder Models…

200 papers

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…

Machine Learning · Computer Science 2024-04-02 Uladzislau Yorsh , Martin Holeňa , Ondřej Bojar , David Herel

Recent advances in transformer-based models have drawn attention to exploring these techniques in medical image segmentation, especially in conjunction with the U-Net model (or its variants), which has shown great success in medical image…

Image and Video Processing · Electrical Eng. & Systems 2021-10-22 Xiangyi Yan , Hao Tang , Shanlin Sun , Haoyu Ma , Deying Kong , Xiaohui Xie

Vision transformers have delivered tremendous success in representation learning. This is primarily due to effective token mixing through self attention. However, this scales quadratically with the number of pixels, which becomes infeasible…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 John Guibas , Morteza Mardani , Zongyi Li , Andrew Tao , Anima Anandkumar , Bryan Catanzaro

The recently developed transformer networks have achieved impressive performance in image denoising by exploiting the self-attention (SA) in images. However, the existing methods mostly use a relatively small window to compute SA due to the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Shi Guo , Hongwei Yong , Xindong Zhang , Jianqi Ma , Lei Zhang

Benefiting from powerful convolutional neural networks (CNNs), learning-based image inpainting methods have made significant breakthroughs over the years. However, some nature of CNNs (e.g. local prior, spatially shared parameters) limit…

Computer Vision and Pattern Recognition · Computer Science 2023-05-22 Ye Deng , Siqi Hui , Sanping Zhou , Deyu Meng , Jinjun Wang

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li

Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing. Recent work shows that the attention mechanism inside Transformer may not be…

Computation and Language · Computer Science 2022-10-27 Yile Wang , Linyi Yang , Zhiyang Teng , Ming Zhou , Yue Zhang

Recently, neural machine translation has achieved remarkable progress by introducing well-designed deep neural networks into its encoder-decoder framework. From the optimization perspective, residual connections are adopted to improve…

Computation and Language · Computer Science 2018-07-03 Yanyao Shen , Xu Tan , Di He , Tao Qin , Tie-Yan Liu

The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Zhang Cheng , Haocheng Wan , Xinyi Shen , Zizhao Wu

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into…

Sound · Computer Science 2025-02-11 Adam Stooke , Rohit Prabhavalkar , Khe Chai Sim , Pedro Moreno Mengibar

Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to…

Computation and Language · Computer Science 2023-02-24 Rui Zhao , Jian Xue , Partha Parthasarathy , Veljko Miljanic , Jinyu Li

We investigate the capability of a transformer pretrained on natural language to generalize to other modalities with minimal finetuning -- in particular, without finetuning of the self-attention and feedforward layers of the residual…

Machine Learning · Computer Science 2021-07-01 Kevin Lu , Aditya Grover , Pieter Abbeel , Igor Mordatch

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. To…

Computation and Language · Computer Science 2023-07-20 Jiayu Ding , Shuming Ma , Li Dong , Xingxing Zhang , Shaohan Huang , Wenhui Wang , Nanning Zheng , Furu Wei

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set,…

Machine Learning · Computer Science 2019-05-28 Juho Lee , Yoonho Lee , Jungtaek Kim , Adam R. Kosiorek , Seungjin Choi , Yee Whye Teh

Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottleneck for efficient inference. Prior work on linear or hybrid attention typically replaces…

Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically…

Computation and Language · Computer Science 2022-04-20 Ziyang Luo , Yadong Xi , Jing Ma , Zhiwei Yang , Xiaoxi Mao , Changjie Fan , Rongsheng Zhang

The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract…

Computation and Language · Computer Science 2021-07-05 Yu Shi

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-30 Ching-Feng Yeh , Jay Mahadeokar , Kaustubh Kalgaonkar , Yongqiang Wang , Duc Le , Mahaveer Jain , Kjell Schubert , Christian Fuegen , Michael L. Seltzer

Recent research in deep learning (DL) has investigated the use of the Fast Fourier Transform (FFT) to accelerate the computations involved in Convolutional Neural Networks (CNNs) by replacing spatial convolution with element-wise…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Eduardo Reis , Thangarajah Akilan , Mohammed Khalid