# Pruning Filter in Filter

arXiv: https://arxiv.org/abs/2009.14410 · HTML: https://mlsanity.com/paper/2009.14410/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2020.

## Built on by (most cited first, 30 of 47)

- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [Only Train Once: A One-Shot Neural Network Training And Pruning Framework](https://mlsanity.com/paper/2107.07467/) (2021)
- [Training-free Transformer Architecture Search](https://mlsanity.com/paper/2203.12217/) (2022)
- [OTOV2: Automatic, Generic, User-Friendly](https://mlsanity.com/paper/2303.06862/) (2023)
- [STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs](https://mlsanity.com/paper/2408.01803/) (2024)
- [SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models](https://mlsanity.com/paper/2410.14720/) (2024)
- [RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks](https://mlsanity.com/paper/2105.14797/) (2021)
- [RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging](https://mlsanity.com/paper/2110.01397/) (2021)
- [A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models](https://mlsanity.com/paper/2406.07929/) (2024)
- [Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression](https://mlsanity.com/paper/2502.16638/) (2025)
- [Bi-directional Masks for Efficient N:M Sparse Training](https://mlsanity.com/paper/2302.06058/) (2023)
- [CP3: Channel Pruning Plug-in for Point-based Networks](https://mlsanity.com/paper/2303.13097/) (2023)
- [Differentiable Transportation Pruning](https://mlsanity.com/paper/2307.08483/) (2023)
- [An Effective Information Theoretic Framework for Channel Pruning](https://mlsanity.com/paper/2408.16772/) (2024)
- [OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators](https://mlsanity.com/paper/2312.09411/) (2023)
- [Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion](https://mlsanity.com/paper/2107.06916/) (2021)
- [Dynamic Structure Pruning for Compressing CNNs](https://mlsanity.com/paper/2303.09736/) (2023)
- [Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models](https://mlsanity.com/paper/2309.01479/) (2023)
- [On Accelerating Edge AI: Optimizing Resource-Constrained Environments](https://mlsanity.com/paper/2501.15014/) (2025)
- [Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy](https://mlsanity.com/paper/2111.09635/) (2021)
- [DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning](https://mlsanity.com/paper/2401.09068/) (2024)
- [HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning](https://mlsanity.com/paper/2409.09085/) (2024)
- [FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling](https://mlsanity.com/paper/2501.19122/) (2025)
- [FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition](https://mlsanity.com/paper/2505.21571/) (2025)
- [Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs](https://mlsanity.com/paper/2305.19844/) (2023)
- [Less is More -- Towards parsimonious multi-task models using structured sparsity](https://mlsanity.com/paper/2308.12114/) (2023)
- [SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning](https://mlsanity.com/paper/2110.10842/) (2021)
- [RGP: Neural Network Pruning through Its Regular Graph Structure](https://mlsanity.com/paper/2110.15192/) (2021)
- [Learning Pruned Structure and Weights Simultaneously from Scratch: an Attention based Approach](https://mlsanity.com/paper/2111.02399/) (2021)

## Abstract (arXiv)

Pruning has become a very powerful and effective technique to compress and accelerate modern neural networks. Existing pruning methods can be grouped into two categories: filter pruning (FP) and weight pruning (WP). FP wins at hardware compatibility but loses at the compression ratio compared with WP. To converge the strength of both methods, we propose to prune the filter in the filter. Specifically, we treat a filter F ∈ ℝC× K× K as K × K stripes, i.e., 1× 1 filters ∈ ℝC, then by pruning the stripes instead of the whole filter, we can achieve finer granularity than traditional FP while being hardware friendly. We term our method as SWP (Stripe-Wise Pruning). SWP is implemented by introducing a novel learnable matrix called Filter Skeleton, whose values reflect the shape of each filter. As some recent work has shown that the pruned architecture is more crucial than the inherited important weights, we argue that the architecture of a single filter, i.e., the shape, also matters. Through extensive experiments, we demonstrate that SWP is more effective compared to the previous FP-based methods and achieves the state-of-art pruning ratio on CIFAR-10 and ImageNet datasets without obvious accuracy drop. Code is available at https://github.com/fxmeng/Pruning-Filter-in-Filter