# Straightforward Layer-wise Pruning for More Efficient Visual Adaptation

arXiv: https://arxiv.org/abs/2407.14330 · HTML: https://mlsanity.com/paper/2407.14330/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 19 Jul 2024.

## Builds on (most cited first, 30 of 35)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark](https://mlsanity.com/paper/1910.04867/) (2019)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?](https://mlsanity.com/paper/1706.00712/) (2017)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.15647/) (2023)
- [Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA](https://mlsanity.com/paper/2304.06027/) (2023)
- [Group Fisher Pruning for Practical Network Compression](https://mlsanity.com/paper/2108.00708/) (2021)
- [Layer-adaptive sparsity for the Magnitude-based Pruning](https://mlsanity.com/paper/2010.07611/) (2020)
- [Convolutional Bypasses Are Better Vision Transformer Adapters](https://mlsanity.com/paper/2207.07039/) (2022)
- [Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers](https://mlsanity.com/paper/1802.00124/) (2018)
- [Towards Efficient Visual Adaption via Structural Re-parameterization](https://mlsanity.com/paper/2302.08106/) (2023)
- [Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space](https://mlsanity.com/paper/2201.00814/) (2022)
- [Pro-tuning: Unified Prompt Tuning for Vision Tasks](https://mlsanity.com/paper/2207.14381/) (2022)

## Built on by (most cited first, 1 of 1)

- [Faster Parameter-Efficient Tuning with Token Redundancy Reduction](https://mlsanity.com/paper/2503.20282/) (2025)

## Abstract (arXiv)

Parameter-efficient transfer learning (PETL) aims to adapt large pre-trained models using limited parameters. While most PETL approaches update the added parameters and freeze pre-trained weights during training, the minimal impact of task-specific deep layers on cross-domain data poses a challenge as PETL cannot modify them, resulting in redundant model structures. Structural pruning effectively reduces model redundancy; however, common pruning methods often lead to an excessive increase in stored parameters due to varying pruning structures based on pruning rates and data. Recognizing the storage parameter volume issue, we propose a Straightforward layer-wise pruning method, called SLS, for pruning PETL-transferred models. By evaluating parameters from a feature perspective of each layer and utilizing clustering metrics to assess current parameters based on clustering phenomena in low-dimensional space obtained through t-SNE, SLS facilitates informed pruning decisions. Our study reveals that layer-wise pruning, with a focus on storing pruning indices, addresses storage volume concerns. Notably, mainstream Layer-wise pruning methods may not be suitable for assessing layer importance in PETL-transferred models, where the majority of parameters are pre-trained and have limited relevance to downstream datasets. Comparative analysis against state-of-the-art PETL methods demonstrates that the pruned model achieved a notable balance between model throughput and accuracy. Moreover, SLS effectively reduces storage overhead arising from varying pruned structures while enhancing the accuracy and speed of pruned models compared to conventional pruning methods.