English
Related papers

Related papers: Self-Attentive Ensemble Transformer: Representing …

200 papers

Social group activity recognition is a challenging task extended from group activity recognition, where social groups must be recognized with their activities and group members. Existing methods tackle this task by leveraging region…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Masato Tamura

Attention-based beamformers have recently been shown to be effective for multi-channel speech recognition. However, they are less capable at capturing local information. In this work, we propose a 2D Conv-Attention module which combines…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-18 Bhargav Pulugundla , Yang Gao , Brian King , Gokce Keskin , Harish Mallidi , Minhua Wu , Jasha Droppo , Roland Maas

The Transformer architecture aggregates input information through the self-attention mechanism, but there is no clear understanding of how this information is mixed across the entire model. Additionally, recent works have demonstrated that…

Computation and Language · Computer Science 2022-10-25 Javier Ferrando , Gerard I. Gállego , Marta R. Costa-jussà

In recent years, transformer models have revolutionized Natural Language Processing (NLP), achieving exceptional results across various tasks, including Sentiment Analysis (SA). As such, current state-of-the-art approaches for SA…

Computation and Language · Computer Science 2024-02-27 Itay Etelis , Avi Rosenfeld , Abraham Itzhak Weinberg , David Sarne

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

Computation and Language · Computer Science 2019-02-18 Baosong Yang , Jian Li , Derek Wong , Lidia S. Chao , Xing Wang , Zhaopeng Tu

In the low-data regime, it is difficult to train good supervised models from scratch. Instead practitioners turn to pre-trained models, leveraging transfer learning. Ensembling is an empirically and theoretically appealing way to construct…

Machine Learning · Computer Science 2020-10-20 Basil Mustafa , Carlos Riquelme , Joan Puigcerver , André Susano Pinto , Daniel Keysers , Neil Houlsby

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen

Recently, Transformer-based methods have achieved impressive results in single image super-resolution (SISR). However, the lack of locality mechanism and high complexity limit their application in the field of super-resolution (SR). To…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Ling Zheng , Jinchen Zhu , Jinpeng Shi , Shizhuang Weng

Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks. Many few-shot models have been widely used for relation learning tasks. However, each of these models has a shortage of capturing a…

Computation and Language · Computer Science 2021-05-26 Qing Lin , Yongbin Liu , Wen Wen , Zhihua Tao

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same…

Machine Learning · Computer Science 2024-11-21 Xuechen Zhang , Xiangyu Chang , Mingchen Li , Amit Roy-Chowdhury , Jiasi Chen , Samet Oymak

We propose a graph-oriented attention-based explainability method for tabular data. Tasks involving tabular data have been solved mostly using traditional tree-based machine learning models which have the challenges of feature selection and…

Machine Learning · Computer Science 2024-06-05 Andrea Treviño Gavito , Diego Klabjan , Jean Utke

Ensemble learning is a process by which multiple base learners are strategically generated and combined into one composite learner. There are two features that are essential to an ensemble's performance, the individual accuracies of the…

Machine Learning · Computer Science 2021-09-30 Wenjing Li , Randy C. Paffenroth , David Berthiaume

Model ensemble is an effective strategy in continual learning, which alleviates catastrophic forgetting by interpolating model parameters, achieving knowledge fusion learned from different tasks. However, existing model ensemble methods…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Yuchuan Mao , Zhi Gao , Xiaomeng Fan , Yuwei Wu , Yunde Jia , Chenchen Jing

Transferring a deep neural network trained on one problem to another requires only a small amount of data and little additional computation time. The same behaviour holds for ensembles of deep learning models typically superior to a single…

Machine Learning · Computer Science 2022-06-28 Ilya Shashkov , Nikita Balabin , Evgeny Burnaev , Alexey Zaytsev

This paper presents a novel approach to electricity price forecasting (EPF) using a pure Transformer model. As opposed to other alternatives, no other recurrent network is used in combination to the attention mechanism. Hence, showing that…

Machine Learning · Computer Science 2025-09-11 Oscar Llorente , Jose Portela

Fair scores reward ensemble forecast members that behave like samples from the same distribution as the verifying observations. They are therefore an attractive choice as loss functions to train data-driven ensemble forecasts or…

Atmospheric and Oceanic Physics · Physics 2026-02-18 Christopher David Roberts

Ensembles improve prediction performance and allow uncertainty quantification by aggregating predictions from multiple models. In deep ensembling, the individual models are usually black box neural networks, or recently, partially…

Machine Learning · Statistics 2022-05-26 Lucas Kook , Andrea Götschi , Philipp FM Baumann , Torsten Hothorn , Beate Sick

Training data-driven turbulence models with high fidelity Reynolds stress can be impractical and recently such models have been trained with velocity and pressure measurements. For gradient-based optimization, such as training deep learning…

Fluid Dynamics · Physics 2021-04-19 Carlos A. Michelén Ströfer , Xin-Lei Zhang , Heng Xiao

In modern statistics, interests shift from pursuing the uniformly minimum variance unbiased estimator to reducing mean squared error (MSE) or residual squared error. Shrinkage based estimation and regression methods offer better prediction…

Methodology · Statistics 2025-02-25 Tianyu Zhan , Haoda Fu , Jian Kang

The apparent ``black box'' nature of neural networks is a barrier to adoption in applications where explainability is essential. This paper presents TAME (Trainable Attention Mechanism for Explanations), a method for generating explanation…

Computer Vision and Pattern Recognition · Computer Science 2025-01-30 Mariano Ntrougkas , Nikolaos Gkalelis , Vasileios Mezaris