Diversity-Guided MLP Reduction for Efficient Large Vision Transformers

• URL: http://arxiv.org/abs/2506.08591v1
• Date: Tue, 10 Jun 2025 08:59:27 GMT
• Title: Diversity-Guided MLP Reduction for Efficient Large Vision Transformers
• Authors: Chengchao Shen, Hourun Zhu, Gongfan Fang, Jianxin Wang, Xinchao Wang,
• Abstract summary: Transformer models achieve excellent scaling property, where the performance is improved with the increment of model capacity.<n>Large-scale model parameters lead to an unaffordable cost of computing and memory.<n>We propose a Diversity-Guided Reduction (DGMR) method to significantly reduce the parameters of large vision transformers.
• Score: 54.656502058570226
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Transformer models achieve excellent scaling property, where the performance is improved with the increment of model capacity. However, large-scale model parameters lead to an unaffordable cost of computing and memory. We analyze popular transformer architectures and find that multilayer perceptron (MLP) modules take up the majority of model parameters. To this end, we focus on the recoverability of the compressed models and propose a Diversity-Guided MLP Reduction (DGMR) method to significantly reduce the parameters of large vision transformers with only negligible performance degradation. Specifically, we conduct a Gram-Schmidt weight pruning strategy to eliminate redundant neurons of MLP hidden layer, while preserving weight diversity for better performance recover during distillation. Compared to the model trained from scratch, our pruned model only requires 0.06\% data of LAION-2B (for the training of large vision transformers) without labels (ImageNet-1K) to recover the original performance. Experimental results on several state-of-the-art large vision transformers demonstrate that our method achieves a more than 57.0\% parameter and FLOPs reduction in a near lossless manner. Notably, for EVA-CLIP-E (4.4B), our method accomplishes a 71.5\% parameter and FLOPs reduction without performance degradation. The source code and trained weights are available at https://github.com/visresearch/DGMR.

Related papers

• OP-LoRA: The Blessing of Dimensionality [93.08208871549557]
  Low-rank adapters enable fine-tuning of large models with only a small number of parameters.<n>They often pose optimization challenges, with poor convergence.<n>We introduce an over- parameterized approach that accelerates training without increasing inference costs.<n>We achieve improvements in vision-language tasks and especially notable increases in image generation.
  arXiv  Detail & Related papers  (2024-12-13T18:55:19Z)
• Learning Parameter Sharing with Tensor Decompositions and Sparsity [5.73573685846194]
  We introduce Fine-grained Singular Sharing (FiPS) to compress large-scale Vision Transformers (ViTs) and Large Language Models (LLMs)<n>FiPS employs a shared base and sparse factors to represent neurons across multi-layer perceptron (MLP) modules.<n> Experimental results show that FiPS reduces the parameter budget by 50-75% for DeiT-B and Swin-L and by 40-50% for various Gemma-2 and Llama-3 models.
  arXiv  Detail & Related papers  (2024-11-14T21:29:58Z)
• Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA [38.30350849992281]
  "Recursive" language models share parameters across layers with minimal loss of performance.<n>Recursive Transformers are efficiently from standard pretrained Transformers, but only use a single block of unique layers that is then repeated multiple times in a loop.<n>We show that our models outperform both similar-sized vanilla pretrained models and knowledge distillation baselines.
  arXiv  Detail & Related papers  (2024-10-28T02:15:45Z)
• LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition [4.375744277719009]
  LORTSAR is applied to two leading Transformer-based models, "Hyperformer" and "STEP-CATFormer" Our method can reduce the number of model parameters substantially with negligible degradation or even performance increase in recognition accuracy. This confirms that SVD combined with post-compression fine-tuning can boost model efficiency, paving the way for more sustainable, lightweight, and high-performance technologies in human action recognition.
  arXiv  Detail & Related papers  (2024-07-19T20:19:41Z)
• SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation [53.675725490807615]
  We introduce SDPose, a new self-distillation method for improving the performance of small transformer-based models. SDPose-T obtains 69.7% mAP with 4.4M parameters and 1.8 GFLOPs, while SDPose-S-V2 obtains 73.5% mAP on the MSCOCO validation dataset.
  arXiv  Detail & Related papers  (2024-04-04T15:23:14Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)
• The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers [59.87030906486969]
  This paper studies the curious phenomenon for machine learning models with Transformer architectures that their activation maps are sparse. We show that sparsity is a prevalent phenomenon that occurs for both natural language processing and vision tasks. We discuss how sparsity immediately implies a way to significantly reduce the FLOP count and improve efficiency for Transformers.
  arXiv  Detail & Related papers  (2022-10-12T15:25:19Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)
• Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation [3.3576886095389296]
  We introduce Greenformers, a collection of model efficiency methods to improve the model efficiency of transformer models. We propose a low-rank factorization approach to improve the efficiency of the transformer model called Low-Rank Transformer. We show that Low-Rank Transformer is more suitable for on-device deployment, as it significantly reduces the model size.
  arXiv  Detail & Related papers  (2021-08-24T15:51:40Z)
• Patch Slimming for Efficient Vision Transformers [107.21146699082819]
  We study the efficiency problem for visual transformers by excavating redundant calculation in given networks. We present a novel patch slimming approach that discards useless patches in a top-down paradigm. Experimental results on benchmark datasets demonstrate that the proposed method can significantly reduce the computational costs of vision transformers.
  arXiv  Detail & Related papers  (2021-06-05T09:46:00Z)

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.