paper-with-me

홈 › Papers

D-Score: A Synapse-Inspired Approach for Filter Pruning

2023-08-08 · Doyoung Park, Jinsoo Kim, Jina Nam, Jooyoung Chang, Sang Min Park

This paper introduces a new aspect for determining the rank of the unimportant filters for filter pruning on convolutional neural networks (CNNs). In the human synaptic system, there are two important channels known as excitatory and inhibitory neurotransmitters that transmit a signal from a neuron to a cell. Adopting the neuroscientific perspective, we propose a synapse-inspired filter pruning method, namely Dynamic Score (D-Score). D-Score analyzes the independent importance of positive and negative weights in the filters and ranks the independent importance by assigning scores. Filters having low overall scores, and thus low impact on the accuracy of neural networks are pruned. The experimental results on CIFAR-10 and ImageNet datasets demonstrate the effectiveness of our proposed method by reducing notable amounts of FLOPs and Params without significant Acc. Drop.

📄 PDF Abstract BibTeX arXiv:2308.04470

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN

2024-03-06 · Biswadeep Chakraborty, Beomseok Kang, Harshit Kumar, Saibal Mukhopadhyay

Recurrent Spiking Neural Networks (RSNNs) have emerged as a computationally efficient and brain-inspired learning model. The design of sparse RSNNs with fewer neurons and synapses helps reduce the computational complexit…

Computational EfficiencyDiversityimage-classificationImage Classification

A simple blind-denoising filter inspired by electrically coupled photoreceptors in the retina

2018-06-15 · Yang Yue, Liuyuan He, Gan He, Jian. K. Liu 외

Photoreceptors in the retina are coupled by electrical synapses called "gap junctions". It has long been established that gap junctions increase the signal-to-noise ratio of photoreceptors. Inspired by electrically coupl…

DenoisingSSIM

Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network

2020-02-19 · Haowen Fang, Amar Shrestha, Ziyi Zhao, Qinru Qiu

The recent discovered spatial-temporal information processing capability of bio-inspired Spiking neural networks (SNN) has enabled some interesting models and applications. However designing large-scale and high-performa…

Data Agnostic Filter Gating for Efficient Deep Networks

2020-10-28 · Xiu Su, Shan You, Tao Huang, Hongyan Xu 외

To deploy a well-trained CNN model on low-end computation edge devices, it is usually supposed to compress or prune the model under certain computation budget (e.g., FLOPs). Current filter pruning methods mainly leverage…

IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning

2025-07-10 · Jaeheun Jung, Jaehyuk Lee, Yeajin Lee, Donghun Lee arxiv

Importance-based structured pruning overwhelmingly relies on filter magnitude. This proxy is fundamentally flawed: due to scale invariance, functionally identical filters can receive arbitrarily different importance scor…

Neural Network Compression