A Generic Shared Attention Mechanism for Various Backbone Neural Networks

• URL: http://arxiv.org/abs/2210.16101v2
• Date: Wed, 10 Apr 2024 02:33:57 GMT
• Title: A Generic Shared Attention Mechanism for Various Backbone Neural Networks
• Authors: Zhongzhan Huang, Senwei Liang, Mingfu Liang, Liang Lin,
• Abstract summary: Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
• Score: 53.36677373145012
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individually incorporate newly designed self-attention modules (SAMs) into each layer of the network for granted without fully exploiting their parameters' potential. This leads to suboptimal performance and increased parameter consumption as the network depth increases. To improve this paradigm, in this paper, we first present a counterintuitive but inherent phenomenon: SAMs tend to produce strongly correlated attention maps across different layers, with an average Pearson correlation coefficient of up to 0.85. Inspired by this inherent observation, we propose Dense-and-Implicit Attention (DIA), which directly shares SAMs across layers and employs a long short-term memory module to calibrate and bridge the highly correlated attention maps of different layers, thus improving the parameter utilization efficiency of SAMs. This design of DIA is also consistent with the neural network's dynamical system perspective. Through extensive experiments, we demonstrate that our simple yet effective DIA can consistently enhance various network backbones, including ResNet, Transformer, and UNet, across tasks such as image classification, object detection, and image generation using diffusion models.

Related papers

• CCDepth: A Lightweight Self-supervised Depth Estimation Network with Enhanced Interpretability [11.076431337488973]
  This study proposes a novel hybrid self-supervised depth estimation network, CCDepth, comprising convolutional neural networks (CNNs) and the white-box CRATE network. This novel network uses CNNs and the CRATE modules to extract local and global information in images, respectively, thereby boosting learning efficiency and reducing model size.
  arXiv  Detail & Related papers  (2024-09-30T04:19:40Z)
• Efficient and Accurate Hyperspectral Image Demosaicing with Neural Network Architectures [3.386560551295746]
  This study investigates the effectiveness of neural network architectures in hyperspectral image demosaicing. We introduce a range of network models and modifications, and compare them with classical methods and existing reference network approaches. Results indicate that our networks outperform or match reference models in both datasets demonstrating exceptional performance.
  arXiv  Detail & Related papers  (2023-12-21T08:02:49Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• ADASR: An Adversarial Auto-Augmentation Framework for Hyperspectral and Multispectral Data Fusion [54.668445421149364]
  Deep learning-based hyperspectral image (HSI) super-resolution aims to generate high spatial resolution HSI (HR-HSI) by fusing hyperspectral image (HSI) and multispectral image (MSI) with deep neural networks (DNNs) In this letter, we propose a novel adversarial automatic data augmentation framework ADASR that automatically optimize and augments HSI-MSI sample pairs to enrich data diversity for HSI-MSI fusion.
  arXiv  Detail & Related papers  (2023-10-11T07:30:37Z)
• Understanding Self-attention Mechanism via Dynamical System Perspective [58.024376086269015]
  Self-attention mechanism (SAM) is widely used in various fields of artificial intelligence. We show that intrinsic stiffness phenomenon (SP) in the high-precision solution of ordinary differential equations (ODEs) also widely exists in high-performance neural networks (NN) We show that the SAM is also a stiffness-aware step size adaptor that can enhance the model's representational ability to measure intrinsic SP.
  arXiv  Detail & Related papers  (2023-08-19T08:17:41Z)
• Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis [93.0013343535411]
  We propose a novel type of analysis called Multi-Scale Class Representational Response Similarity Analysis (ClassRepSim) We show that adding STAC modules to ResNet style architectures can result in up to a 1.6% increase in top-1 accuracy. Results from ClassRepSim analysis can be used to select an effective parameterization of the STAC module resulting in competitive performance.
  arXiv  Detail & Related papers  (2023-06-16T18:29:26Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• Ensembles of Spiking Neural Networks [0.3007949058551534]
  This paper demonstrates how to construct ensembles of spiking neural networks producing state-of-the-art results. We achieve classification accuracies of 98.71%, 100.0%, and 99.09%, on the MNIST, NMNIST and DVS Gesture datasets respectively. We formalize spiking neural networks as GLM predictors, identifying a suitable representation for their target domain.
  arXiv  Detail & Related papers  (2020-10-15T17:45:18Z)

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.