NiNformer: A Network in Network Transformer with Token Mixing Generated Gating Function
- URL: http://arxiv.org/abs/2403.02411v4
- Date: Thu, 13 Jun 2024 19:55:19 GMT
- Title: NiNformer: A Network in Network Transformer with Token Mixing Generated Gating Function
- Authors: Abdullah Nazhat Abdullah, Tarkan Aydin,
- Abstract summary: The attention mechanism was utilized in computer vision as the Vision Transformer ViT.
It comes with the drawback of being expensive and requiring datasets of considerable size for effective optimization.
This paper introduces a new computational block as an alternative to the standard ViT block that reduces the compute burdens.
- Score: 1.3812010983144802
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The attention mechanism is the main component of the transformer architecture, and since its introduction, it has led to significant advancements in deep learning that span many domains and multiple tasks. The attention mechanism was utilized in computer vision as the Vision Transformer ViT, and its usage has expanded into many tasks in the vision domain, such as classification, segmentation, object detection, and image generation. While this mechanism is very expressive and capable, it comes with the drawback of being computationally expensive and requiring datasets of considerable size for effective optimization. To address these shortcomings, many designs have been proposed in the literature to reduce the computational burden and alleviate the data size requirements. Examples of such attempts in the vision domain are the MLP-Mixer, the Conv-Mixer, the Perciver-IO, and many more. This paper introduces a new computational block as an alternative to the standard ViT block that reduces the compute burdens by replacing the normal attention layers with a Network in Network structure that enhances the static approach of the MLP-Mixer with a dynamic system of learning an element-wise gating function by a token mixing process. Extensive experimentation shows that the proposed design provides better performance than the baseline architectures on multiple datasets applied in the image classification task of the vision domain.
Related papers
- You Only Need Less Attention at Each Stage in Vision Transformers [19.660385306028047]
Vision Transformers (ViTs) capture the global information of images through self-attention modules.
We propose the Less-Attention Vision Transformer (LaViT), which computes only a few attention operations at each stage.
Our architecture demonstrates exceptional performance across various vision tasks including classification, detection and segmentation.
arXiv Detail & Related papers (2024-06-01T12:49:16Z) - Multiscale Low-Frequency Memory Network for Improved Feature Extraction
in Convolutional Neural Networks [13.815116154370834]
We introduce a novel framework, the Multiscale Low-Frequency Memory (MLFM) Network.
The MLFM efficiently preserves low-frequency information, enhancing performance in targeted computer vision tasks.
Our work builds upon the existing CNN foundations and paves the way for future advancements in computer vision.
arXiv Detail & Related papers (2024-03-13T00:48:41Z) - Vision Transformer with Quadrangle Attention [76.35955924137986]
We propose a novel quadrangle attention (QA) method that extends the window-based attention to a general quadrangle formulation.
Our method employs an end-to-end learnable quadrangle regression module that predicts a transformation matrix to transform default windows into target quadrangles.
We integrate QA into plain and hierarchical vision transformers to create a new architecture named QFormer, which offers minor code modifications and negligible extra computational cost.
arXiv Detail & Related papers (2023-03-27T11:13:50Z) - Vision Transformer with Convolutions Architecture Search [72.70461709267497]
We propose an architecture search method-Vision Transformer with Convolutions Architecture Search (VTCAS)
The high-performance backbone network searched by VTCAS introduces the desirable features of convolutional neural networks into the Transformer architecture.
It enhances the robustness of the neural network for object recognition, especially in the low illumination indoor scene.
arXiv Detail & Related papers (2022-03-20T02:59:51Z) - Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution [50.10987776141901]
Recent vision transformers along with self-attention have achieved promising results on various computer vision tasks.
We introduce an effective hybrid architecture for super-resolution (SR) tasks, which leverages local features from CNNs and long-range dependencies captured by transformers.
Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.
arXiv Detail & Related papers (2022-03-15T06:52:25Z) - A Simple Single-Scale Vision Transformer for Object Localization and
Instance Segmentation [79.265315267391]
We propose a simple and compact ViT architecture called Universal Vision Transformer (UViT)
UViT achieves strong performance on object detection and instance segmentation tasks.
arXiv Detail & Related papers (2021-12-17T20:11:56Z) - Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences.
The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
arXiv Detail & Related papers (2021-05-29T05:26:07Z) - Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain.
In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden.
Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
arXiv Detail & Related papers (2021-03-15T12:54:26Z) - Multi-stage Attention ResU-Net for Semantic Segmentation of
Fine-Resolution Remote Sensing Images [9.398340832493457]
We propose a Linear Attention Mechanism (LAM) to address this issue.
LAM is approximately equivalent to dot-product attention with computational efficiency.
We design a Multi-stage Attention ResU-Net for semantic segmentation from fine-resolution remote sensing images.
arXiv Detail & Related papers (2020-11-29T07:24:21Z)
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.