English
Related papers

Related papers: DeepCrossAttention: Supercharging Transformer Resi…

200 papers

Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…

Machine Learning · Computer Science 2026-01-21 Xiaojie Xia , Huigang Zhang , Chaoliang Zhong , Jun Sun , Yusuke Oishi

Transformers have captured growing attention in computer vision, thanks to its large capacity and global processing capabilities. However, transformers are data hungry, and their ability to generalize is constrained compared to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Hosam S. EL-Assiouti , Hadeer El-Saadawy , Maryam N. Al-Berry , Mohamed F. Tolba

Transformer-based neural decoders have emerged as a promising approach to error correction coding, combining data-driven adaptability with efficient modeling of long-range dependencies. This paper presents a novel decoder architecture that…

Information Theory · Computer Science 2025-09-22 Chin Wa Lau , Xiang Shi , Ziyan Zheng , Haiwen Cao , Nian Guo

Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not…

Computation and Language · Computer Science 2021-03-23 Hao Peng , Nikolaos Pappas , Dani Yogatama , Roy Schwartz , Noah A. Smith , Lingpeng Kong

Effectively detecting anomalous nodes in attributed networks is crucial for the success of many real-world applications such as fraud and intrusion detection. Existing approaches have difficulties with three major issues: sparsity and…

Machine Learning · Computer Science 2020-10-01 Yulong Pei , Tianjin Huang , Werner van Ipenburg , Mykola Pechenizkiy

Transformer architectures are now central to sequence modeling tasks. At its heart is the attention mechanism, which enables effective modeling of long-term dependencies in a sequence. Recently, transformers have been successfully applied…

Computer Vision and Pattern Recognition · Computer Science 2022-06-16 Lin Zheng , Huijie Pan , Lingpeng Kong

We propose a cross-attention Transformer for joint decoding of uplink OFDM signals received by multiple coordinated access points. A shared per-receiver encoder learns the time-frequency structure of each grid, and a token-wise…

Signal Processing · Electrical Eng. & Systems 2026-04-08 Xavier Tardy , Grégoire Lefebvre , Apostolos Kountouris , Haïfa Fares , Amor Nafkha

Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either…

Computer Vision and Pattern Recognition · Computer Science 2023-03-17 Xixi Wang , Xiao Wang , Bo Jiang , Jin Tang , Bin Luo

The transformer architecture by Vaswani et al. (2017) is now ubiquitous across application domains, from natural language processing to speech processing and image understanding. We propose DenseFormer, a simple modification to the standard…

Computation and Language · Computer Science 2024-03-22 Matteo Pagliardini , Amirkeivan Mohtashami , Francois Fleuret , Martin Jaggi

In recent years, employing layer attention to enhance interaction among hierarchical layers has proven to be a significant advancement in building network structures. In this paper, we delve into the distinction between layer attention and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Kaishen Wang , Xun Xia , Jian Liu , Zhang Yi , Tao He

Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…

Machine Learning · Computer Science 2019-07-03 Sainbayar Sukhbaatar , Edouard Grave , Guillaume Lample , Herve Jegou , Armand Joulin

We present a novel architecture for dense correspondence. The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggregation. However, they generally aggregate one or the other…

Computer Vision and Pattern Recognition · Computer Science 2022-09-21 Sunghwan Hong , Seokju Cho , Seungryong Kim , Stephen Lin

In this paper, we present DAT, a Depth-Aware Transformer framework designed for camera-based 3D detection. Our model is based on observing two major issues in existing methods: large depth translation errors and duplicate predictions along…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Hao Zhang , Hongyang Li , Ailing Zeng , Feng Li , Shilong Liu , Xingyu Liao , Lei Zhang

With the development of feed-forward models, the default model for sequence modeling has gradually evolved to replace recurrent networks. Many powerful feed-forward models based on convolutional networks and attention mechanism were…

Computation and Language · Computer Science 2023-10-17 Hongyan Hao , Yan Wang , Siqiao Xue , Yudi Xia , Jian Zhao , Furao Shen

Residual networks (Resnets) have become a prominent architecture in deep learning. However, a comprehensive understanding of Resnets is still a topic of ongoing research. A recent view argues that Resnets perform iterative refinement of…

Computer Vision and Pattern Recognition · Computer Science 2018-03-09 Stanisław Jastrzębski , Devansh Arpit , Nicolas Ballas , Vikas Verma , Tong Che , Yoshua Bengio

Although attention-based Neural Machine Translation has achieved remarkable progress in recent layers, it still suffers from issue of making insufficient use of the output of each layer. In transformer, it only uses the top layer of encoder…

Computation and Language · Computer Science 2021-08-02 GuoLiang Li , Yiyang Li

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional…

Machine Learning · Computer Science 2025-08-07 Claudius Gros

An extension of Transformers is proposed that enables explicit relational reasoning through a novel module called the Abstractor. At the core of the Abstractor is a variant of attention called relational cross-attention. The approach is…

Machine Learning · Statistics 2024-04-16 Awni Altabaa , Taylor Webb , Jonathan Cohen , John Lafferty

Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing methods dedicate to developing more sophisticated attention…

Computer Vision and Pattern Recognition · Computer Science 2020-04-08 Qilong Wang , Banggu Wu , Pengfei Zhu , Peihua Li , Wangmeng Zuo , Qinghua Hu

Neural networks are known to produce poor uncertainty estimations, and a variety of approaches have been proposed to remedy this issue. This includes deep ensemble, a simple and effective method that achieves state-of-the-art results for…

Machine Learning · Computer Science 2022-10-13 Yuesong Shen , Daniel Cremers
‹ Prev 1 4 5 6 7 8 10 Next ›