paper-with-me

홈 › Papers

EZCrop: Energy-Zoned Channels for Robust Output Pruning

2021-05-08 · Rui Lin, Jie Ran, Dongpeng Wang, King Hung Chiu, Ngai Wong

Recent results have revealed an interesting observation in a trained convolutional neural network (CNN), namely, the rank of a feature map channel matrix remains surprisingly constant despite the input images. This has led to an effective rank-based channel pruning algorithm, yet the constant rank phenomenon remains mysterious and unexplained. This work aims at demystifying and interpreting such rank behavior from a frequency-domain perspective, which as a bonus suggests an extremely efficient Fast Fourier Transform (FFT)-based metric for measuring channel importance without explicitly computing its rank. We achieve remarkable CNN channel pruning based on this analytically sound and computationally efficient metric and adopt it for repetitive pruning to demonstrate robustness via our scheme named Energy-Zoned Channels for Robust Output Pruning (EZCrop), which shows consistently better results than other state-of-the-art channel pruning methods.

📄 PDF Abstract BibTeX arXiv:2105.03679

Code (1)

RuiLin0212/EZCrop 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge

2026-03-18 · Mohamed Mejri, Ashiqur Rasul, Abhijit Chatterjee arxiv

Modern convolutional neural networks (CNNs) are workhorses for video and image processing, but fail to adapt to the computational complexity of input samples in a dynamic manner to minimize energy consumption. In this re…

Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

2026-05-20 · Qishi Zhan, Ziheng Chen, Minxuan Hu arxiv

One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-prun…

Data-free Backdoor Removal based on Channel Lipschitzness

2022-08-05 · Runkai Zheng, Rongjun Tang, Jianze Li, Li Liu

Recent studies have shown that Deep Neural Networks (DNNs) are vulnerable to the backdoor attacks, which leads to malicious behaviors of DNNs when specific triggers are attached to the input images. It was further demons…

Spectral Complex Autoencoder Pruning: A Fidelity-Guided Criterion for Extreme Structured Channel Compression

2026-01-14 · Wei Liu, Xing Deng, Haijian Shao, Yingtao Jiang arxiv

We propose Spectral Complex Autoencoder Pruning (SCAP), a reconstruction-based criterion that measures functional redundancy at the level of individual output channels. For each convolutional layer, we construct a comple…

Spectral Reconstruction

Operation-Aware Soft Channel Pruning using Differentiable Masks

2020-07-08 · ICML 2020 1 · Minsoo Kang, Bohyung Han

We propose a simple but effective data-driven channel pruning algorithm, which compresses deep neural networks in a differentiable way by exploiting the characteristics of operations. The proposed approach makes a joint …