You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet

• URL: http://arxiv.org/abs/2405.21022v1
• Date: Fri, 31 May 2024 17:09:16 GMT
• Title: You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet
• Authors: Zhen Qin, Yuxin Mao, Xuyang Shen, Dong Li, Jing Zhang, Yuchao Dai, Yiran Zhong,
• Abstract summary: We develop an efficient multi-dimensional sequential modeling framework called LightNet based on the new recurrence. We present two new multi-dimensional linear relative positional encoding methods, MD-TPE and MD-LRPE, to enhance the model's ability to discern positional information in multi-dimensional scenarios.
• Score: 47.48142221329556
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Linear attention mechanisms have gained prominence in causal language models due to their linear computational complexity and enhanced speed. However, the inherent decay mechanism in linear attention presents challenges when applied to multi-dimensional sequence modeling tasks, such as image processing and multi-modal learning. In these scenarios, the utilization of sequential scanning to establish a global receptive field necessitates multiple scans for multi-dimensional data, thereby leading to inefficiencies. This paper identifies the inefficiency caused by a multiplicative linear recurrence and proposes an efficient alternative additive linear recurrence to avoid the issue, as it can handle multi-dimensional data within a single scan. We further develop an efficient multi-dimensional sequential modeling framework called LightNet based on the new recurrence. Moreover, we present two new multi-dimensional linear relative positional encoding methods, MD-TPE and MD-LRPE to enhance the model's ability to discern positional information in multi-dimensional scenarios. Our empirical evaluations across various tasks, including image classification, image generation, bidirectional language modeling, and autoregressive language modeling, demonstrate the efficacy of LightNet, showcasing its potential as a versatile and efficient solution for multi-dimensional sequential modeling.

Related papers

• MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model [49.931663904599205]
  MaVEn is an innovative framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. We show that MaVEn significantly enhances MLLMs' understanding in complex multi-image scenarios, while also improving performance in single-image contexts.
  arXiv  Detail & Related papers  (2024-08-22T11:57:16Z)
• Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning [49.197385954021456]
  In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for visualization and subsequent analysis tasks. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. Most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios.
  arXiv  Detail & Related papers  (2024-06-10T02:20:26Z)
• Enhancing Deep Learning Models through Tensorization: A Comprehensive Survey and Framework [0.0]
  This paper explores the steps involved in multidimensional data sources, various multiway analysis methods employed, and the benefits of these approaches. A small example of Blind Source Separation (BSS) is presented comparing 2-dimensional algorithms and a multiway algorithm in Python. Results indicate that multiway analysis is more expressive.
  arXiv  Detail & Related papers  (2023-09-05T17:56:22Z)
• Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation [2.5556910002263984]
  Score-based diffusion models (SBDM) have emerged as state-of-the-art approaches for image generation. This paper develops SBDMs in the infinite-dimensional setting, that is, we model the training data as functions supported on a rectangular domain. We demonstrate how to overcome two shortcomings of current SBDM approaches in the infinite-dimensional setting.
  arXiv  Detail & Related papers  (2023-03-08T18:10:10Z)
• A Model-data-driven Network Embedding Multidimensional Features for Tomographic SAR Imaging [5.489791364472879]
  We propose a new model-data-driven network to achieve tomoSAR imaging based on multi-dimensional features. We add two 2D processing modules, both convolutional encoder-decoder structures, to enhance multi-dimensional features of the imaging scene effectively. Compared with the conventional CS-based FISTA method and DL-based gamma-Net method, the result of our proposed method has better performance on completeness while having decent imaging accuracy.
  arXiv  Detail & Related papers  (2022-11-28T02:01:43Z)
• FAS-UNet: A Novel FAS-driven Unet to Learn Variational Image Segmentation [3.741136641573471]
  We propose a novel variational-model-informed network (FAS-Unet) that exploits the model and algorithm priors to extract the multi-scale features. The proposed network integrates image data and mathematical models, and implements them through learning a few convolution kernels. Experimental results show that the proposed FAS-Unet is very competitive with other state-of-the-art methods in qualitative, quantitative and model complexity evaluations.
  arXiv  Detail & Related papers  (2022-10-27T04:15:16Z)
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning [68.9515120904028]
  Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the building block.
  arXiv  Detail & Related papers  (2020-07-21T11:48:22Z)
• Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond [62.730497582218284]
  We develop a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation. We conduct two groups of image registration experiments on 3D volume datasets including image-to-atlas registration on brain MRI data and image-to-image registration on liver CT data.
  arXiv  Detail & Related papers  (2020-04-30T03:23:45Z)
• Learning Bijective Feature Maps for Linear ICA [73.85904548374575]
  We show that existing probabilistic deep generative models (DGMs) which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. We create models that converge quickly, are easy to train, and achieve better unsupervised latent factor discovery than flow-based models, linear ICA, and Variational Autoencoders on images.
  arXiv  Detail & Related papers  (2020-02-18T17:58:07Z)
• Concurrently Extrapolating and Interpolating Networks for Continuous Model Generation [34.72650269503811]
  We propose a simple yet effective model generation strategy to form a sequence of models that only requires a set of specific-effect label images. We show that the proposed method is capable of producing a series of continuous models and achieves better performance than that of several state-of-the-art methods for image smoothing.
  arXiv  Detail & Related papers  (2020-01-12T04:44:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.