English
Related papers

Related papers: DeepCrossAttention: Supercharging Transformer Resi…

200 papers

We study the capabilities of the transformer architecture with varying depth. Specifically, we designed a novel set of sequence learning tasks to systematically evaluate and comprehend how the depth of transformer affects its ability to…

Machine Learning · Computer Science 2024-04-03 Xingwu Chen , Difan Zou

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Laziz U. Abdullaev , Maksim Tkachenko , Tan M. Nguyen

Bearing fault detection is a critical task in predictive maintenance, where accurate and timely fault identification can prevent costly downtime and equipment damage. Traditional attention mechanisms in Transformer neural networks often…

Machine Learning · Computer Science 2024-12-17 Marzieh Mirzaeibonehkhater , Mohammad Ali Labbaf-Khaniki , Mohammad Manthouri

We present lambda layers -- an alternative framework to self-attention -- for capturing long-range interactions between an input and structured contextual information (e.g. a pixel surrounded by other pixels). Lambda layers capture such…

Computer Vision and Pattern Recognition · Computer Science 2021-02-18 Irwan Bello

Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restores sharpened…

Computer Vision and Pattern Recognition · Computer Science 2015-04-28 Chao Dong , Yubin Deng , Chen Change Loy , Xiaoou Tang

Multi-Head Attention (MHA) is a key component of Transformer. In MHA, attention heads work independently, causing problems such as low-rank bottleneck of attention score matrices and head redundancy. We propose Dynamically Composable…

Machine Learning · Computer Science 2024-06-05 Da Xiao , Qingye Meng , Shengping Li , Xingyuan Yuan

Several recent works demonstrate that transformers can implement algorithms like gradient descent. By a careful construction of weights, these works show that multiple layers of transformers are expressive enough to simulate iterations of…

Machine Learning · Computer Science 2023-11-13 Kwangjun Ahn , Xiang Cheng , Hadi Daneshmand , Suvrit Sra

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Zihang Dai , Hanxiao Liu , Quoc V. Le , Mingxing Tan

As the superiority of context information gradually manifests in advanced semantic segmentation, learning to capture the compact context relationship can help to understand the complex scenes. In contrast to some previous works utilizing…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Yifu Liu , Chenfeng Xu , Xinyu Jin

Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Jiahui Wang , Zhenyou Wang , Shanna Zhuang , Hui Wang

Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow. In this work, we explore whether more layers are beneficial to graph transformers, and find that current…

Machine Learning · Computer Science 2023-03-02 Haiteng Zhao , Shuming Ma , Dongdong Zhang , Zhi-Hong Deng , Furu Wei

While features of different scales are perceptually important to visual inputs, existing vision transformers do not yet take advantage of them explicitly. To this end, we first propose a cross-scale vision transformer, CrossFormer. It…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Wenxiao Wang , Wei Chen , Qibo Qiu , Long Chen , Boxi Wu , Binbin Lin , Xiaofei He , Wei Liu

Transformers have recently been utilized to perform object detection and tracking in the context of autonomous driving. One unique characteristic of these models is that attention weights are computed in each forward pass, giving insights…

Computer Vision and Pattern Recognition · Computer Science 2022-10-27 Felicia Ruppel , Florian Faion , Claudius Gläser , Klaus Dietmayer

Federated learning enables cooperative training among massively distributed clients by sharing their learned local model parameters. However, with increasing model size, deploying federated learning requires a large communication bandwidth,…

Machine Learning · Computer Science 2022-12-13 Rui Song , Liguo Zhou , Lingjuan Lyu , Andreas Festag , Alois Knoll

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Machine Learning · Computer Science 2025-11-11 Hanwen Liu , Yixuan Ma , Shi Jin , Yuguang Wang

At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to…

Medical image segmentation, a critical application of semantic segmentation in healthcare, has seen significant advancements through specialized computer vision techniques. While deep learning-based medical image segmentation is essential…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Fuchen Zheng , Quanjun Li , Weixuan Li , Xuhang Chen , Yihang Dong , Guoheng Huang , Chi-Man Pun , Shoujun Zhou

Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while…

Computer Vision and Pattern Recognition · Computer Science 2020-05-15 Shuang Li , Chi Harold Liu , Qiuxia Lin , Binhui Xie , Zhengming Ding , Gao Huang , Jian Tang

Time series forecasting is crucial for applications across multiple domains and various scenarios. Although Transformer models have dramatically advanced the landscape of forecasting, their effectiveness remains debated. Recent findings…

Machine Learning · Computer Science 2024-12-24 Dongbin Kim , Jinseong Park , Jaewook Lee , Hoki Kim

Most deep trackers still follow the guidance of the siamese paradigms and use a template that contains only the target without any contextual information, which makes it difficult for the tracker to cope with large appearance changes, rapid…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Kaijie He , Canlong Zhang , Sheng Xie , Zhixin Li , Zhiwen Wang