MOR-VIT: Efficient Vision Transformer with Mixture-of-Recursions

• URL: http://arxiv.org/abs/2507.21761v1
• Date: Tue, 29 Jul 2025 12:46:36 GMT
• Title: MOR-VIT: Efficient Vision Transformer with Mixture-of-Recursions
• Authors: YiZhou Li,
• Abstract summary: MoR-ViT is a novel vision transformer framework that incorporates a token-level dynamic recursion mechanism.<n>Experiments on ImageNet-1K and transfer benchmarks demonstrate that MoR-ViT achieves state-of-the-art accuracy with up to 70% parameter reduction and 2.5x inference acceleration.
• Score: 1.0411839100853515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformers (ViTs) have achieved remarkable success in image recognition, yet standard ViT architectures are hampered by substantial parameter redundancy and high computational cost, limiting their practical deployment. While recent efforts on efficient ViTs primarily focus on static model compression or token-level sparsification, they remain constrained by fixed computational depth for all tokens. In this work, we present MoR-ViT, a novel vision transformer framework that, for the first time, incorporates a token-level dynamic recursion mechanism inspired by the Mixture-of-Recursions (MoR) paradigm. This approach enables each token to adaptively determine its processing depth, yielding a flexible and input-dependent allocation of computational resources. Extensive experiments on ImageNet-1K and transfer benchmarks demonstrate that MoR-ViT not only achieves state-of-the-art accuracy with up to 70% parameter reduction and 2.5x inference acceleration, but also outperforms leading efficient ViT baselines such as DynamicViT and TinyViT under comparable conditions. These results establish dynamic recursion as an effective strategy for efficient vision transformers and open new avenues for scalable and deployable deep learning models in real-world scenarios.

Related papers

• DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs [124.52164183968145]
  We present DyMU, an efficient, training-free framework that reduces the computational burden of vision-language models (VLMs)<n>Our approach comprises two key components. First, Dynamic Token Merging (DToMe) reduces the number of visual token embeddings by merging similar tokens based on image complexity.<n>Second, Virtual Token Unmerging (VTU) simulates the expected token sequence for large language models (LLMs) by efficiently reconstructing the attention dynamics of a full sequence.
  arXiv  Detail & Related papers  (2025-04-23T18:38:18Z)
• ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale Stages [0.0]
  Vision Transformers (ViTs) have revolutionized computer vision by leveraging self-attention to model long-range dependencies.<n>We propose the Efficient Convolutional Vision Transformer (ECViT), a hybrid architecture that effectively combines the strengths of CNNs and Transformers.
  arXiv  Detail & Related papers  (2025-04-21T03:00:17Z)
• LPViT: Low-Power Semi-structured Pruning for Vision Transformers [43.126752035656196]
  Vision transformers have emerged as a promising alternative to convolutional neural networks for image analysis tasks.<n>One significant drawback of ViTs is their resource-intensive nature, leading to increased memory footprint, complexity, and power consumption.<n>We introduce a new block-structured pruning to address the resource-intensive issue for ViTs, offering a balanced trade-off between accuracy and hardware acceleration.
  arXiv  Detail & Related papers  (2024-07-02T08:58:19Z)
• Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference [14.030836300221756]
  textbfSparse-Tuning is a novel PEFT method that accounts for the information redundancy in images and videos. Sparse-Tuning minimizes the quantity of tokens processed at each layer, leading to a quadratic reduction in computational and memory overhead. Our results show that our Sparse-Tuning reduces GFLOPs to textbf62%-70% of the original ViT-B while achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-05-23T15:34:53Z)
• Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation [67.13876021157887]
  Dynamic Tuning (DyT) is a novel approach to improve both parameter and inference efficiency for ViT adaptation. DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.
  arXiv  Detail & Related papers  (2024-03-18T14:05:52Z)
• ViR: Towards Efficient Vision Retention Backbones [97.93707844681893]
  We propose a new class of computer vision models, dubbed Vision Retention Networks (ViR) ViR has dual parallel and recurrent formulations, which strike an optimal balance between fast inference and parallel training with competitive performance. We have validated the effectiveness of ViR through extensive experiments with different dataset sizes and various image resolutions.
  arXiv  Detail & Related papers  (2023-10-30T16:55:50Z)
• CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models [22.055655390093722]
  Correlation Aware Pruner (CAP) significantly pushes the compressibility limits for state-of-the-art architectures. New theoretically-justified pruner handles complex weight correlations accurately and efficiently during the pruning process itself. We show for the first time that extremely-accurate large vision models, trained via self-supervised techniques, can also be pruned to moderate sparsities, with negligible accuracy loss.
  arXiv  Detail & Related papers  (2022-10-14T12:19:09Z)
• Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer [56.87383229709899]
  We develop an information rectification module (IRM) and a distribution guided distillation scheme for fully quantized vision transformers (Q-ViT) Our method achieves a much better performance than the prior arts.
  arXiv  Detail & Related papers  (2022-10-13T04:00:29Z)
• Deeper Insights into ViTs Robustness towards Common Corruptions [82.79764218627558]
  We investigate how CNN-like architectural designs and CNN-based data augmentation strategies impact on ViTs' robustness towards common corruptions. We demonstrate that overlapping patch embedding and convolutional Feed-Forward Network (FFN) boost performance on robustness. We also introduce a novel conditional method enabling input-varied augmentations from two angles.
  arXiv  Detail & Related papers  (2022-04-26T08:22:34Z)
• A Unified Pruning Framework for Vision Transformers [40.7622551128182]
  Vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. We propose a unified framework for structural pruning of both ViTs and its variants, namely UP-ViTs. Our method focuses on pruning all ViTs components while maintaining the consistency of the model structure.
  arXiv  Detail & Related papers  (2021-11-30T05:01:02Z)
• 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)

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.