# Retrain or not retrain? -- efficient pruning methods of deep CNN networks

arXiv: https://arxiv.org/abs/2002.07051 · HTML: https://mlsanity.com/paper/2002.07051/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 6 of 6)

- [LoFiT: Localized Fine-tuning on LLM Representations](https://mlsanity.com/paper/2406.01563/) (2024)
- [Deep Learning on Home Drone: Searching for the Optimal Architecture](https://mlsanity.com/paper/2209.11064/) (2022)
- [Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction](https://mlsanity.com/paper/2112.15445/) (2021)
- [Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting](https://mlsanity.com/paper/2308.07939/) (2023)
- [Towards Building Efficient Sentence BERT Models using Layer Pruning](https://mlsanity.com/paper/2409.14168/) (2024)
- [Towards efficient deep autoencoders for multivariate time series anomaly detection](https://mlsanity.com/paper/2403.02429/) (2024)

## Abstract (arXiv)

Convolutional neural networks (CNN) play a major role in image processing tasks like image classification, object detection, semantic segmentation. Very often CNN networks have from several to hundred stacked layers with several megabytes of weights. One of the possible methods to reduce complexity and memory footprint is pruning. Pruning is a process of removing weights which connect neurons from two adjacent layers in the network. The process of finding near optimal solution with specified drop in accuracy can be more sophisticated when DL model has higher number of convolutional layers. In the paper few approaches based on retraining and no retraining are described and compared together.