English
Related papers

Related papers: PoNet: Pooling Network for Efficient Token Mixing …

200 papers

Transformer models cannot easily scale to long sequences due to their O(N^2) time and space complexity. This has led to Transformer variants seeking to lower computational complexity, such as Longformer and Performer. While such models have…

Computation and Language · Computer Science 2024-12-10 Guanghui Qin , Yukun Feng , Benjamin Van Durme

Visual saliency prediction using transformers - Convolutional neural networks (CNNs) have significantly advanced computational modelling for saliency prediction. However, accurately simulating the mechanisms of visual attention in the human…

Multimedia · Computer Science 2022-06-30 Jianxun Lou , Hanhe Lin , David Marshall , Dietmar Saupe , Hantao Liu

Transformer and its variants are fundamental neural architectures in deep learning. Recent works show that learning attention in the Fourier space can improve the long sequence learning capability of Transformers. We argue that wavelet…

Computation and Language · Computer Science 2023-05-24 Yufan Zhuang , Zihan Wang , Fangbo Tao , Jingbo Shang

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-10 Nithin Rao Koluguri , Travis Bartley , Hainan Xu , Oleksii Hrinchuk , Jagadeesh Balam , Boris Ginsburg , Georg Kucsko

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Computation and Language · Computer Science 2020-12-03 Iz Beltagy , Matthew E. Peters , Arman Cohan

Recently, the superior performance of Transformers has made them a more robust and scalable solution for sequence modeling than traditional recurrent neural networks (RNNs). However, the effectiveness of Transformer in capturing long-term…

Machine Learning · Computer Science 2025-05-07 Zhou Wu , Junyi An , Baile Xu , Furao Shen , Jian Zhao

Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…

Machine Learning · Computer Science 2019-11-13 Yao-Hung Hubert Tsai , Shaojie Bai , Makoto Yamada , Louis-Philippe Morency , Ruslan Salakhutdinov

Recently many effective attention modules are proposed to boot the model performance by exploiting the internal information of convolutional neural networks in computer vision. In general, many previous works ignore considering the design…

Machine Learning · Computer Science 2022-10-25 Shanshan Zhong , Wushao Wen , Jinghui Qin

Transformers have reached remarkable success in sequence modeling. However, these models have efficiency issues as they need to store all the history token-level representations as memory. We present Memformer, an efficient neural network…

Computation and Language · Computer Science 2022-04-14 Qingyang Wu , Zhenzhong Lan , Kun Qian , Jing Gu , Alborz Geramifard , Zhou Yu

Heavy computation is a bottleneck limiting deep-learningbased feature matching algorithms to be applied in many realtime applications. However, existing lightweight networks optimized for Euclidean data cannot address classical feature…

Computer Vision and Pattern Recognition · Computer Science 2023-03-13 Xiaoyong Lu , Yaping Yan , Bin Kang , Songlin Du

This paper proposes Omnidirectional Representations from Transformers (OmniNet). In OmniNet, instead of maintaining a strictly horizontal receptive field, each token is allowed to attend to all tokens in the entire network. This process can…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Yi Tay , Mostafa Dehghani , Vamsi Aribandi , Jai Gupta , Philip Pham , Zhen Qin , Dara Bahri , Da-Cheng Juan , Donald Metzler

Neural networks using transformer-based architectures have recently demonstrated great power and flexibility in modeling sequences of many types. One of the core components of transformer networks is the attention layer, which allows…

Machine Learning · Computer Science 2019-07-16 Matthew Spellings

Current end-to-end machine reading and question answering (Q\&A) models are primarily based on recurrent neural networks (RNNs) with attention. Despite their success, these models are often slow for both training and inference due to the…

Computation and Language · Computer Science 2018-04-26 Adams Wei Yu , David Dohan , Minh-Thang Luong , Rui Zhao , Kai Chen , Mohammad Norouzi , Quoc V. Le

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Sound · Computer Science 2019-07-03 Miquel India , Pooyan Safari , Javier Hernando

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

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

Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…

Computer Vision and Pattern Recognition · Computer Science 2021-11-01 Athanasios Papadopoulos , Paweł Korus , Nasir Memon

In this paper, we propose Mixture of Layer-Wise Tokens (MoLT), a parameter- and memory-efficient adaptation framework for audio-visual learning. The key idea of MoLT is to replace conventional, computationally heavy sequential adaptation at…

Sound · Computer Science 2025-12-02 Kyeongha Rho , Hyeongkeun Lee , Jae Won Cho , Joon Son Chung

Recent studies show that self-attentions behave like low-pass filters (as opposed to convolutions) and enhancing their high-pass filtering capability improves model performance. Contrary to this idea, we investigate existing…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Guhnoo Yun , Juhan Yoo , Kijung Kim , Jeongho Lee , Dong Hwan Kim

Deep learning has recently garnered significant interest in wireless communications due to its superior performance compared to traditional model-based algorithms. Deep convolutional neural networks (CNNs) have demonstrated notable…

Signal Processing · Electrical Eng. & Systems 2025-09-22 SaiKrishna Saketh Yellapragada , Esa Ollila , Mario Costa