English
Related papers

Related papers: Differentiable Window for Dynamic Local Attention

200 papers

Differentiable programming is the combination of classical neural networks modules with algorithmic ones in an end-to-end differentiable model. These new models, that use automatic differentiation to calculate gradients, have new learning…

Dynamical Systems · Mathematics 2020-05-05 Adrián Hernández , José M. Amigó

Transformer-based LLMs have achieved exceptional performance across a wide range of NLP tasks. However, the standard self-attention mechanism suffers from quadratic time complexity and linearly increased cache size. Sliding window attention…

Computation and Language · Computer Science 2025-01-03 Yixing Xu , Shivank Nag , Dong Li , Lu Tian , Emad Barsoum

Channel attention mechanisms in convolutional neural networks have been proven to be effective in various computer vision tasks. However, the performance improvement comes with additional model complexity and computation cost. In this…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Krushi Patel , Guanghui Wang

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention…

Computer Vision and Pattern Recognition · Computer Science 2022-05-30 Kai Liu , Tianyi Wu , Cong Liu , Guodong Guo

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

Recently, Transformers have shown promising performance in various vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute, especially for the high-resolution vision tasks. Local…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Zhemin Zhang , Xun Gong

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

Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation. Recently, visual attention models have been applied to automatically localize the discriminative regions of…

Computer Vision and Pattern Recognition · Computer Science 2018-02-27 Bo Zhao , Xiao Wu , Jiashi Feng , Qiang Peng , Shuicheng Yan

Attention within windows has been widely explored in vision transformers to balance the performance, computation complexity, and memory footprint. However, current models adopt a hand-crafted fixed-size window design, which restricts their…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Qiming Zhang , Yufei Xu , Jing Zhang , Dacheng Tao

Deep learning models are often not easily adaptable to new tasks and require task-specific adjustments. The differentiable neural computer (DNC), a memory-augmented neural network, is designed as a general problem solver which can be used…

Computation and Language · Computer Science 2018-07-10 Jörg Franke , Jan Niehues , Alex Waibel

We develop a framework for combining differentiable programming languages with neural networks. Using this framework we create end-to-end trainable systems that learn to write interpretable algorithms with perceptual components. We explore…

Machine Learning · Computer Science 2017-03-03 Alexander L. Gaunt , Marc Brockschmidt , Nate Kushman , Daniel Tarlow

DIFF Transformer improves attention allocation by enhancing focus on relevant context while suppressing noise. It introduces a differential attention mechanism that calculates the difference between two independently generated attention…

Machine Learning · Computer Science 2025-12-17 Yueyang Cang , Yuhang Liu , Xiaoteng Zhang , Li Shi , Wenge Que

We propose DiffCLIP, a novel vision-language model that extends the differential attention mechanism to CLIP architectures. Differential attention was originally developed for large language models to amplify relevant context while…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Hasan Abed Al Kader Hammoud , Bernard Ghanem

To address the high resolution of image pixels, the Swin Transformer introduces window attention. This mechanism divides an image into non-overlapping windows and restricts attention computation to within each window, significantly…

Computer Vision and Pattern Recognition · Computer Science 2025-01-15 Zhendong Zhang

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of…

Computation and Language · Computer Science 2023-12-15 Kaiqiang Song , Xiaoyang Wang , Sangwoo Cho , Xiaoman Pan , Dong Yu

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

Speech emotion recognition is crucial to human-computer interaction. The temporal regions that represent different emotions scatter in different parts of the speech locally. Moreover, the temporal scales of important information may vary…

Sound · Computer Science 2023-03-06 Shuaiqi Chen , Xiaofen Xing , Weibin Zhang , Weidong Chen , Xiangmin Xu

Transformer tends to overallocate attention to irrelevant context. In this work, we introduce Diff Transformer, which amplifies attention to the relevant context while canceling noise. Specifically, the differential attention mechanism…

Computation and Language · Computer Science 2025-04-08 Tianzhu Ye , Li Dong , Yuqing Xia , Yutao Sun , Yi Zhu , Gao Huang , Furu Wei

Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years. Most of the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Furong Duan , Tao Zhu , Jinqiang Wang , Liming Chen , Huansheng Ning , Yaping Wan

Differential Transformer has recently been proposed to improve performance in Transformer models by canceling out noise through a denoiser attention mechanism. In this work, we introduce DiffLoRA, a parameter-efficient adaptation of the…

Computation and Language · Computer Science 2025-08-01 Alexandre Misrahi , Nadezhda Chirkova , Maxime Louis , Vassilina Nikoulina
‹ Prev 1 2 3 10 Next ›