paper-with-me

홈 › Papers

MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning

2019-03-25 · ICCV 2019 10 · Zechun Liu, Haoyuan Mu, Xiangyu Zhang, Zichao Guo, Xin Yang, Tim Kwang-Ting Cheng, Jian Sun

In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure given the target network. We use a simple stochastic structure sampling method for training the PruningNet. Then, we apply an evolutionary procedure to search for good-performing pruned networks. The search is highly efficient because the weights are directly generated by the trained PruningNet and we do not need any finetuning at search time. With a single PruningNet trained for the target network, we can search for various Pruned Networks under different constraints with little human participation. Compared to the state-of-the-art pruning methods, we have demonstrated superior performances on MobileNet V1/V2 and ResNet. Codes are available on https://github.com/liuzechun/MetaPruning.

📄 PDF Abstract BibTeX arXiv:1903.10258

Code (2)

liuzechun/MetaPruning 공식 구현 pytorch
megvii-model/MetaPruning pytorch

Tasks

AutoMLMeta-Learning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks

2022-06-02 · Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li 외

Efficient deep neural network (DNN) models equipped with compact operators (e.g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e.g., the total number of weights/operations)…

Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning

2019-11-25 · Ilchae Jung, Kihyun You, Hyeonwoo Noh, Minsu Cho 외

We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few …

Meta-LearningObjectObject Tracking

Achieving Fair Skin Lesion Detection through Skin Tone Normalization and Channel Pruning

2025-09-24 · Zihan Wei, Tapabrata Chakraborti arxiv

Recent works have shown that deep learning based skin lesion image classification models trained on unbalanced dataset can exhibit bias toward protected demographic attributes such as race, age,and gender. Current bias m…

Image ClassificationData Augmentation

Automatic Channel Pruning for Multi-Head Attention

2024-05-31 · Eunho Lee, Youngbae Hwang

Despite the strong performance of Transformers, their quadratic computation complexity presents challenges in applying them to vision tasks. Automatic pruning is one of effective methods for reducing computation complexi…

DHP: Differentiable Meta Pruning via HyperNetworks

2020-03-30 · ECCV 2020 8 · Yawei Li, Shuhang Gu, Kai Zhang, Luc van Gool 외

Network pruning has been the driving force for the acceleration of neural networks and the alleviation of model storage/transmission burden. With the advent of AutoML and neural architecture search (NAS), pruning has bec…

AutoMLDenoisingimage-classificationImage Classification+5