English
Related papers

Related papers: Active Token Mixer

200 papers

Transformers achieve state-of-the-art results across many tasks, but their uniform application of quadratic self-attention to every token at every layer makes them computationally expensive. We introduce DTRNet (Dynamic Token Routing…

Until quite recently, the backbone of nearly every state-of-the-art computer vision model has been the 2D convolution. At its core, a 2D convolution simultaneously mixes information across both the spatial and channel dimensions of a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 George Cazenavette , Joel Julin , Simon Lucey

Machine learning potentials (MLPs) trained on data from quantum-mechanics based first-principles methods can approach the accuracy of the reference method at a fraction of the computational cost. To facilitate efficient MLP-based molecular…

Materials Science · Physics 2021-08-17 Michael S. Chen , Tobias Morawietz , Hideki Mori , Thomas E. Markland , Nongnuch Artrith

Standard neural machine translation (NMT) is on the assumption that the document-level context is independent. Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while…

Computation and Language · Computer Science 2021-08-25 Shu Jiang , Rui Wang , Zuchao Li , Masao Utiyama , Kehai Chen , Eiichiro Sumita , Hai Zhao , Bao-liang Lu

Industrial recommender systems critically depend on high-quality ranking models. However, traditional pipelines still rely on manual feature engineering and scenario-specific architectures, which hinder cross-scenario transfer and…

Information Retrieval · Computer Science 2025-10-20 Xianyang Qi , Yuan Tian , Zhaoyu Hu , Zhirui Kuai , Chang Liu , Hongxiang Lin , Lei Wang

Transformers are deep architectures that define "in-context mappings" which enable predicting new tokens based on a given set of tokens (such as a prompt in NLP applications or a set of patches for a vision transformer). In this work, we…

Computation and Language · Computer Science 2024-10-04 Takashi Furuya , Maarten V. de Hoop , Gabriel Peyré

Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are passively hidden in the CNN's increasing receptive fields or…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Dong Zhang , Hanwang Zhang , Jinhui Tang , Meng Wang , Xiansheng Hua , Qianru Sun

The rapid advancement in large foundation models is propelling the paradigm shifts across various industries. One significant change is that agents, instead of traditional machines or humans, will be the primary participants in the future…

Signal Processing · Electrical Eng. & Systems 2025-07-30 Zhuoran Xiao , Chenhui Ye , Yijia Feng , Yunbo Hu , Tianyu Jiao , Liyu Cai , Guangyi Liu

Large language models (LLMs) exhibit a strong capacity for in-context learning: Given labeled examples, they can generate good predictions without parameter updates. However, many interactive settings go beyond static prediction to online…

Machine Learning · Computer Science 2026-05-12 Emile Anand , Abdullah Ateyeh , Xinyuan Cao , Max Dabagia

Despite the remarkable capabilities of deep neural networks in image recognition, the dependence on activation functions remains a largely unexplored area and has yet to be eliminated. On the other hand, Polynomial Networks is a class of…

Computer Vision and Pattern Recognition · Computer Science 2024-02-01 Yixin Cheng , Grigorios G. Chrysos , Markos Georgopoulos , Volkan Cevher

In this paper, we propose Two-Stream AMTnet, which leverages recent advances in video-based action representation[1] and incremental action tube generation[2]. Majority of the present action detectors follow a frame-based representation, a…

Computer Vision and Pattern Recognition · Computer Science 2020-04-06 Suman Saha , Gurkirt Singh , Fabio Cuzzolin

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Dongchen Han , Tianzhu Ye , Yizeng Han , Zhuofan Xia , Siyuan Pan , Pengfei Wan , Shiji Song , Gao Huang

Convolutional neural networks are widely used in various segmentation tasks in medical images. However, they are challenged to learn global features adaptively due to the inherent locality of convolutional operations. In contrast, MLP…

Image and Video Processing · Electrical Eng. & Systems 2024-12-25 Jin Yang , Xiaobing Yu , Peijie Qiu

Transformer-based models have achieved great success in various NLP, vision, and speech tasks. However, the core of Transformer, the self-attention mechanism, has a quadratic time and memory complexity with respect to the sequence length,…

Computation and Language · Computer Science 2023-05-23 Chao-Hong Tan , Qian Chen , Wen Wang , Qinglin Zhang , Siqi Zheng , Zhen-Hua Ling

We propose Joint MLP/Attention (JoMA) dynamics, a novel mathematical framework to understand the training procedure of multilayer Transformer architectures. This is achieved by integrating out the self-attention layer in Transformers,…

Machine Learning · Computer Science 2024-03-18 Yuandong Tian , Yiping Wang , Zhenyu Zhang , Beidi Chen , Simon Du

MLP-Mixer has newly appeared as a new challenger against the realm of CNNs and transformer. Despite its simplicity compared to transformer, the concept of channel-mixing MLPs and token-mixing MLPs achieves noticeable performance in visual…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Jaesung Choe , Chunghyun Park , Francois Rameau , Jaesik Park , In So Kweon

In recent years, transformer-based deep learning networks have gained popularity in Hyperspectral (HS) unmixing applications due to their superior performance. The attention mechanism within transformers facilitates input-dependent…

Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Yikai Wang , Xinghao Chen , Lele Cao , Wenbing Huang , Fuchun Sun , Yunhe Wang

This paper investigates the role of global context for crowd counting. Specifically, a pure transformer is used to extract features with global information from overlapping image patches. Inspired by classification, we add a context token…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Guolei Sun , Yun Liu , Thomas Probst , Danda Pani Paudel , Nikola Popovic , Luc Van Gool

In order to successfully perform tasks specified by natural language instructions, an artificial agent operating in a visual world needs to map words, concepts, and actions from the instruction to visual elements in its environment. This…

Computer Vision and Pattern Recognition · Computer Science 2019-10-15 Soumik Dasgupta , Badri N. Patro , Vinay P. Namboodiri
‹ Prev 1 3 4 5 6 7 10 Next ›