ParFormer: Vision Transformer Baseline with Parallel Local Global Token Mixer and Convolution Attention Patch Embedding

• URL: http://arxiv.org/abs/2403.15004v1
• Date: Fri, 22 Mar 2024 07:32:21 GMT
• Title: ParFormer: Vision Transformer Baseline with Parallel Local Global Token Mixer and Convolution Attention Patch Embedding
• Authors: Novendra Setyawan, Ghufron Wahyu Kurniawan, Chi-Chia Sun, Jun-Wei Hsieh, Hui-Kai Su, Wen-Kai Kuo,
• Abstract summary: ParFormer is an enhanced transformer architecture that allows the incorporation of different token mixers into a single stage. We offer the Convolutional Attention Patch Embedding (CAPE) as an enhancement of standard patch embedding to improve token mixer extraction. Our model variants with 11M, 23M, and 34M parameters achieve scores of 80.4%, 82.1%, and 83.1%, respectively.
• Score: 3.4140488674588614
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work presents ParFormer as an enhanced transformer architecture that allows the incorporation of different token mixers into a single stage, hence improving feature extraction capabilities. Integrating both local and global data allows for precise representation of short- and long-range spatial relationships without the need for computationally intensive methods such as shifting windows. Along with the parallel token mixer encoder, We offer the Convolutional Attention Patch Embedding (CAPE) as an enhancement of standard patch embedding to improve token mixer extraction with a convolutional attention module. Our comprehensive evaluation demonstrates that our ParFormer outperforms CNN-based and state-of-the-art transformer-based architectures in image classification and several complex tasks such as object recognition. The proposed CAPE has been demonstrated to benefit the overall MetaFormer architecture, even while utilizing the Identity Mapping Token Mixer, resulting in a 0.5\% increase in accuracy. The ParFormer models outperformed ConvNeXt and Swin Transformer for the pure convolution and transformer model in accuracy. Furthermore, our model surpasses the current leading hybrid transformer by reaching competitive Top-1 scores in the ImageNet-1K classification test. Specifically, our model variants with 11M, 23M, and 34M parameters achieve scores of 80.4\%, 82.1\%, and 83.1\%, respectively. Code: https://github.com/novendrastywn/ParFormer-CAPE-2024

Related papers

• Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers [56.37495946212932]
  Vision transformers (ViTs) have demonstrated their superior accuracy for computer vision tasks compared to convolutional neural networks (CNNs) This work proposes Quasar-ViT, a hardware-oriented quantization-aware architecture search framework for ViTs.
  arXiv  Detail & Related papers  (2024-07-25T16:35:46Z)
• SeTformer is What You Need for Vision and Language [26.036537788653373]
  Self-optimal Transport (SeT) is a novel transformer for achieving better performance and computational efficiency. SeTformer achieves impressive top-1 accuracies of 84.7% and 86.2% on ImageNet-1K. SeTformer also achieves state-of-the-art results in language modeling on the GLUE benchmark.
  arXiv  Detail & Related papers  (2024-01-07T16:52:49Z)
• Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts [60.1586169973792]
  M$3$ViT is the latest multi-task ViT model that introduces mixture-of-experts (MoE) MoE achieves better accuracy and over 80% reduction computation but leaves challenges for efficient deployment on FPGA. Our work, dubbed Edge-MoE, solves the challenges to introduce the first end-to-end FPGA accelerator for multi-task ViT with a collection of architectural innovations.
  arXiv  Detail & Related papers  (2023-05-30T02:24:03Z)
• EdgeYOLO: An Edge-Real-Time Object Detector [69.41688769991482]
  This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS 2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone 2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia
  arXiv  Detail & Related papers  (2023-02-15T06:05:14Z)
• EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications [68.35683849098105]
  We introduce split depth-wise transpose attention (SDTA) encoder that splits input tensors into multiple channel groups. Our EdgeNeXt model with 1.3M parameters achieves 71.2% top-1 accuracy on ImageNet-1K. Our EdgeNeXt model with 5.6M parameters achieves 79.4% top-1 accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-06-21T17:59:56Z)
• EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers [29.09883780571206]
  We propose EdgeFormer, a pure ConvNet based backbone model. We combine the global circular convolution (GCC) with position embeddings, a light-weight convolution op. Experiment results show that the proposed EdgeFormer achieves better performance than popular light-weight ConvNets and vision transformer based models.
  arXiv  Detail & Related papers  (2022-03-08T09:25:17Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Pipeline Parallelism for Inference on Heterogeneous Edge Computing [9.745025902229882]
  Deep neural networks with large model sizes achieve state-of-the-art results for tasks in computer vision (CV) and natural language processing (NLP) These large-scale models are too compute- or memory-intensive for resource-constrained edge devices. We propose EdgePipe, a distributed framework for edge systems that uses pipeline parallelism to both speed up inference and enable running larger models that otherwise cannot fit on single edge devices.
  arXiv  Detail & Related papers  (2021-10-28T05:20:51Z)
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers [105.74546828182834]
  We show a hardware-efficient dynamic inference regime, named dynamic weight slicing, which adaptively slice a part of network parameters for inputs with diverse difficulty levels. We present dynamic slimmable network (DS-Net) and dynamic slice-able network (DS-Net++) by input-dependently adjusting filter numbers of CNNs and multiple dimensions in both CNNs and transformers.
  arXiv  Detail & Related papers  (2021-09-21T09:57:21Z)
• Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks [9.409651543514615]
  This work introduces convolutional layers with pre-defined sparse 2D kernels that have support sets that repeat periodically within and across filters. Due to the efficient storage of our periodic sparse kernels, the parameter savings can translate into considerable improvements in energy efficiency.
  arXiv  Detail & Related papers  (2020-01-29T07:10:56Z)

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.