# Retraining-Free Depth Pruning of Vision Transformers: A Cross Domain Study of Layer Redundancy

arXiv: https://arxiv.org/abs/2610.15005 · HTML: https://mlsanity.com/paper/2610.15005/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 58 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [The Unreasonable Ineffectiveness of the Deeper Layers](https://mlsanity.com/paper/2403.17887/) (2024)
- [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021)
- [What Matters in Transformers? Not All Attention is Needed](https://mlsanity.com/paper/2406.15786/) (2024)
- [Vision Transformer Pruning](https://mlsanity.com/paper/2104.08500/) (2021)
- [X-Pruner: eXplainable Pruning for Vision Transformers](https://mlsanity.com/paper/2303.04935/) (2023)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [WHOI-Plankton- A Large Scale Fine Grained Visual Recognition Benchmark Dataset for Plankton Classification](https://mlsanity.com/paper/1510.00745/) (2015)
- [MLP Can Be A Good Transformer Learner](https://mlsanity.com/paper/2404.05657/) (2024)
- [LPViT: Low-Power Semi-structured Pruning for Vision Transformers](https://mlsanity.com/paper/2407.02068/) (2024)
- [ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization](https://mlsanity.com/paper/2505.02819/) (2025)
- [Tree Species Identification from Bark Images Using Convolutional Neural Networks](https://mlsanity.com/paper/1803.00949/) (2018)
- [Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework](https://mlsanity.com/paper/2411.18376/) (2024)
- [Deep Learning Classification of Lake Zooplankton](https://mlsanity.com/paper/2108.05258/) (2021)
- [Dense Vision Transformer Compression with Few Samples](https://mlsanity.com/paper/2403.18708/) (2024)
- [DAPlankton: Benchmark Dataset for Multi-instrument Plankton Recognition via Fine-grained Domain Adaptation](https://mlsanity.com/paper/2402.05615/) (2024)
- [Variance-Based Pruning for Accelerating and Compressing Trained Networks](https://mlsanity.com/paper/2507.12988/) (2025)

## Abstract (arXiv)

Transformer architectures have achieved strong results in natural language processing and computer vision, but their deployment is limited by high computational, memory and storage costs, motivating research into model compression techniques, such as pruning, while preserving performance. Prior work has shown substantial redundancy in large language models (LLMs), and redundancy in vision transformers has also been investigated, but it remains less systematically analyzed than in LLMs. In this work, we extend similarity-based redundancy analysis to vision models by measuring cosine similarity between layer inputs and outputs to identify transformations with minimal impact. We study redundancy patterns across several transformer architectures and find that deep vision transformers such as DINOv2 and SwinV2, like language models, exhibit significant redundancy. We then evaluate how this redundancy can be exploited to improve efficiency, analyzing the trade-off between inference speed and performance degradation under different pruning strategies. Our results show that moderate pruning can yield substantial acceleration with limited impact on accuracy, and that 20% of the DINOv2 blocks can be removed without any retraining, for a 1.24x throughput gain and a 20% lower energy per image at a relative accuracy loss below 1% on ImageNet-1K. We further propose a model selection pipeline that automatically identifies the best pruned configuration for a given dataset, reducing FLOPs by 13% to 27% on average across architectures with an average accuracy change between -0.3 and +1.0 points.