# Channel Pruning Guided by Classification Loss and Feature Importance

arXiv: https://arxiv.org/abs/2003.06757 · HTML: https://mlsanity.com/paper/2003.06757/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2020.

## Built on by (most cited first, 17 of 17)

- [CHEX: CHannel EXploration for CNN Model Compression](https://mlsanity.com/paper/2203.15794/) (2022)
- [PTQ4SAM: Post-Training Quantization for Segment Anything](https://mlsanity.com/paper/2405.03144/) (2024)
- [Carrying out CNN Channel Pruning in a White Box](https://mlsanity.com/paper/2104.11883/) (2021)
- [BiBench: Benchmarking and Analyzing Network Binarization](https://mlsanity.com/paper/2301.11233/) (2023)
- [RobustMQ: Benchmarking Robustness of Quantized Models](https://mlsanity.com/paper/2308.02350/) (2023)
- [Unsupervised Learning of Accurate Siamese Tracking](https://mlsanity.com/paper/2204.01475/) (2022)
- [LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment](https://mlsanity.com/paper/2410.21352/) (2024)
- [LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit](https://mlsanity.com/paper/2508.09981/) (2025)
- [CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Network](https://mlsanity.com/paper/2105.12386/) (2021)
- [EPSD: Early Pruning with Self-Distillation for Efficient Model Compression](https://mlsanity.com/paper/2402.00084/) (2024)
- [PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models](https://mlsanity.com/paper/2412.07268/) (2024)
- [Model Compression using Progressive Channel Pruning](https://mlsanity.com/paper/2507.04792/) (2025)
- [Fused Depthwise Tiling for Memory Optimization in TinyML Deep Neural Network Inference](https://mlsanity.com/paper/2303.17878/) (2023)
- [SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment](https://mlsanity.com/paper/2511.13023/) (2025)
- [Prioritized Subnet Sampling for Resource-Adaptive Supernet Training](https://mlsanity.com/paper/2109.05432/) (2021)
- [Toward domain generalized pruning by scoring out-of-distribution importance](https://mlsanity.com/paper/2210.13810/) (2022)
- [AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks](https://mlsanity.com/paper/2108.13591/) (2021)

## Abstract (arXiv)

In this work, we propose a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI). In contrast to the existing layer-by-layer channel pruning approaches that only consider how to reconstruct the features from the next layer, our approach additionally take the classification loss into account in the channel pruning process. We also observe that some reconstructed features will be removed at the next pruning stage. So it is unnecessary to reconstruct these features. To this end, we propose a new strategy to suppress the influence of unimportant features (i.e., the features will be removed at the next pruning stage). Our comprehensive experiments on three benchmark datasets, i.e., CIFAR-10, ImageNet, and UCF-101, demonstrate the effectiveness of our CPLI method.