English
Related papers

Related papers: Differential Gated Self-Attention

200 papers

Simultaneous machine translation (SiMT) outputs translation while receiving the streaming source inputs, and hence needs a policy to determine where to start translating. The alignment between target and source words often implies the most…

Computation and Language · Computer Science 2022-03-18 Shaolei Zhang , Yang Feng

Transformer models have achieved profound success in prediction tasks in a wide range of applications in natural language processing, speech recognition and computer vision. Extending Transformer's success to safety-critical domains…

Machine Learning · Computer Science 2025-09-11 Wenlong Chen , Yingzhen Li

Graph Transformers (GTs) have recently achieved significant success in the graph domain by effectively capturing both long-range dependencies and graph inductive biases. However, these methods face two primary challenges: (1) multi-view…

Machine Learning · Computer Science 2025-01-03 Xiaotang Wang , Yun Zhu , Haizhou Shi , Yongchao Liu , Chuntao Hong

Generative Adversarial Networks (GANs) produce impressive results on unconditional image generation when powered with large-scale image datasets. Yet generated images are still easy to spot especially on datasets with high variance (e.g.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-21 Ning Yu , Guilin Liu , Aysegul Dundar , Andrew Tao , Bryan Catanzaro , Larry Davis , Mario Fritz

Human behavior understanding requires looking at minute details in the large context of a scene containing multiple input modalities. It is necessary as it allows the design of more human-like machines. While transformer approaches have…

Computer Vision and Pattern Recognition · Computer Science 2022-12-09 Tanay Agrawal , Michal Balazia , Philipp Müller , François Brémond

Over the past decade, Deep Convolutional Neural Networks have been widely adopted for medical image segmentation and shown to achieve adequate performance. However, due to the inherent inductive biases present in the convolutional…

Computer Vision and Pattern Recognition · Computer Science 2021-07-08 Jeya Maria Jose Valanarasu , Poojan Oza , Ilker Hacihaliloglu , Vishal M. Patel

Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases. However, directly applying the transformer structure to remove noise is…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Kangliang Liu , Xiangcheng Du , Sijie Liu , Yingbin Zheng , Xingjiao Wu , Cheng Jin

Active noise control typically employs adaptive filtering to generate secondary noise, where the least mean square algorithm is the most widely used. However, traditional updating rules are linear and exhibit limited effectiveness in…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-30 Pengxing Feng , Hing Cheung So

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…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Long Zhao , Zizhao Zhang , Ting Chen , Dimitris N. Metaxas , Han Zhang

Transformer self-attention can be interpreted as a gradient flow on the unit sphere, in which tokens evolve under softmax interaction potentials and tend to form clusters. While prior work has established clustering behavior for single-head…

Machine Learning · Computer Science 2026-05-11 Ayan Pendharkar

The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Nam Hyeon-Woo , Kim Yu-Ji , Byeongho Heo , Dongyoon Han , Seong Joon Oh , Tae-Hyun Oh

Many studies have been conducted to improve the efficiency of Transformer from quadric to linear. Among them, the low-rank-based methods aim to learn the projection matrices to compress the sequence length. However, the projection matrices…

Machine Learning · Computer Science 2022-11-30 Bosheng Qin , Juncheng Li , Siliang Tang , Yueting Zhuang

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Computation and Language · Computer Science 2021-09-13 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong

Enabled by multi-head self-attention, Transformer has exhibited remarkable results in speech emotion recognition (SER). Compared to the original full attention mechanism, window-based attention is more effective in learning fine-grained…

Sound · Computer Science 2023-02-28 Weidong Chen , Xiaofen Xing , Xiangmin Xu , Jianxin Pang , Lan Du

Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initialization remains challenging and computationally expensive. In this paper, we propose two…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Hongyi Pan , Emadeldeen Hamdan , Xin Zhu , Ahmet Enis Cetin , Ulas Bagci

Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical analysis of the…

Machine Learning · Computer Science 2022-06-27 Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Cyril Zhang

Existing generative adversarial networks (GANs) for speech enhancement solely rely on the convolution operation, which may obscure temporal dependencies across the sequence input. To remedy this issue, we propose a self-attention layer…

Multi-headed Attention's (MHA) quadratic compute and linearly growing KV-cache make long-context transformers expensive to train and serve. Prior works such as Grouped Query Attention (GQA) and Multi-Latent Attention (MLA) shrink the cache,…

Computation and Language · Computer Science 2026-03-18 Tomas Figliolia , Nicholas Alonso , Rishi Iyer , Quentin Anthony , Beren Millidge

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, where much recent progress has been made by the advancement of representation learning techniques and inspiration of human behaviors.…

Computation and Language · Computer Science 2021-06-10 Kun Zhang , Guangyi Lv , Meng Wang , Enhong Chen

The rise of highly convincing synthetic speech poses a growing threat to audio communications. Although existing Audio Deepfake Detection (ADD) methods have demonstrated good performance under clean conditions, their effectiveness drops…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-05 Haohan Shi , Xiyu Shi , Safak Dogan , Tianjin Huang , Yunxiao Zhang