Rethinking Vision Transformer Depth via Structural Reparameterization

• URL: http://arxiv.org/abs/2511.19718v1
• Date: Mon, 24 Nov 2025 21:28:55 GMT
• Title: Rethinking Vision Transformer Depth via Structural Reparameterization
• Authors: Chengwei Zhou, Vipin Chaudhary, Gourav Datta,
• Abstract summary: We propose a branch-based structural reparameterization technique that operates during the training phase.<n>Our approach leverages parallel branches within transformer blocks that can be systematically consolidated into streamlined single-path models.<n>When applied to ViT-Tiny, the framework successfully reduces the original 12-layer architecture to 6, 4, or as few as 3 layers while maintaining classification accuracy on ImageNet-1K.
• Score: 16.12815682992294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The computational overhead of Vision Transformers in practice stems fundamentally from their deep architectures, yet existing acceleration strategies have primarily targeted algorithmic-level optimizations such as token pruning and attention speedup. This leaves an underexplored research question: can we reduce the number of stacked transformer layers while maintaining comparable representational capacity? To answer this, we propose a branch-based structural reparameterization technique that operates during the training phase. Our approach leverages parallel branches within transformer blocks that can be systematically consolidated into streamlined single-path models suitable for inference deployment. The consolidation mechanism works by gradually merging branches at the entry points of nonlinear components, enabling both feed-forward networks (FFN) and multi-head self-attention (MHSA) modules to undergo exact mathematical reparameterization without inducing approximation errors at test time. When applied to ViT-Tiny, the framework successfully reduces the original 12-layer architecture to 6, 4, or as few as 3 layers while maintaining classification accuracy on ImageNet-1K. The resulting compressed models achieve inference speedups of up to 37% on mobile CPU platforms. Our findings suggest that the conventional wisdom favoring extremely deep transformer stacks may be unnecessarily restrictive, and point toward new opportunities for constructing efficient vision transformers.

Related papers

• Pieceformer: Similarity-Driven Knowledge Transfer via Scalable Graph Transformer in VLSI [10.727382706747592]
  Pieceformer is a scalable, self-supervised similarity assessment framework.<n>It reduces mean absolute error (MAE) by 24.9% over the baseline.<n>It is the only method to correctly cluster all real-world design groups.
  arXiv  Detail & Related papers  (2025-06-18T22:47:09Z)
• BHViT: Binarized Hybrid Vision Transformer [53.38894971164072]
  Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN)<n>We propose BHViT, a binarization-friendly hybrid ViT architecture and its full binarization model with the guidance of three important observations.<n>Our proposed algorithm achieves SOTA performance among binary ViT methods.
  arXiv  Detail & Related papers  (2025-03-04T08:35:01Z)
• PointMT: Efficient Point Cloud Analysis with Hybrid MLP-Transformer Architecture [46.266960248570086]
  This study tackles the quadratic complexity of the self-attention mechanism by introducing a complexity local attention mechanism for effective feature aggregation. We also introduce a parameter-free channel temperature adaptation mechanism that adaptively adjusts the attention weight distribution in each channel. We show that PointMT achieves performance comparable to state-of-the-art methods while maintaining an optimal balance between performance and accuracy.
  arXiv  Detail & Related papers  (2024-08-10T10:16:03Z)
• Self-Supervised Pre-Training for Table Structure Recognition Transformer [25.04573593082671]
  We propose a self-supervised pre-training (SSP) method for table structure recognition transformers. We discover that the performance gap between the linear projection transformer and the hybrid CNN-transformer can be mitigated by SSP of the visual encoder in the TSR model.
  arXiv  Detail & Related papers  (2024-02-23T19:34:06Z)
• 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)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Global Vision Transformer Pruning with Hessian-Aware Saliency [93.33895899995224]
  This work challenges the common design philosophy of the Vision Transformer (ViT) model with uniform dimension across all the stacked blocks in a model stage. We derive a novel Hessian-based structural pruning criteria comparable across all layers and structures, with latency-aware regularization for direct latency reduction. Performing iterative pruning on the DeiT-Base model leads to a new architecture family called NViT (Novel ViT), with a novel parameter that utilizes parameters more efficiently.
  arXiv  Detail & Related papers  (2021-10-10T18:04:59Z)
• TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecasting [6.393659160890665]
  We propose the concept of tightly-coupled convolutional Transformer(TCCT) and three TCCT architectures. Our experiments on real-world datasets show that our TCCT architectures could greatly improve the performance of existing state-of-art Transformer models.
  arXiv  Detail & Related papers  (2021-08-29T08:49:31Z)
• Augmented Shortcuts for Vision Transformers [49.70151144700589]
  We study the relationship between shortcuts and feature diversity in vision transformer models. We present an augmented shortcut scheme, which inserts additional paths with learnable parameters in parallel on the original shortcuts. Experiments conducted on benchmark datasets demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2021-06-30T09:48:30Z)
• 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)
• Incorporating Convolution Designs into Visual Transformers [24.562955955312187]
  We propose a new textbfConvolution-enhanced image Transformer (CeiT) which combines the advantages of CNNs in extracting low-level features, strengthening locality, and the advantages of Transformers in establishing long-range dependencies. Experimental results on ImageNet and seven downstream tasks show the effectiveness and generalization ability of CeiT compared with previous Transformers and state-of-the-art CNNs, without requiring a large amount of training data and extra CNN teachers.
  arXiv  Detail & Related papers  (2021-03-22T13:16:12Z)

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.