paper-with-me

홈 › Papers

Cascaded channel pruning using hierarchical self-distillation

2020-08-16 · Roy Miles, Krystian Mikolajczyk

In this paper, we propose an approach for filter-level pruning with hierarchical knowledge distillation based on the teacher, teaching-assistant, and student framework. Our method makes use of teaching assistants at intermediate pruning levels that share the same architecture and weights as the target student. We propose to prune each model independently using the gradient information from its corresponding teacher. By considering the relative sizes of each student-teacher pair, this formulation provides a natural trade-off between the capacity gap for knowledge distillation and the bias of the filter saliency updates. Our results show improvements in the attainable accuracy and model compression across the CIFAR10 and ImageNet classification tasks using the VGG16and ResNet50 architectures. We provide an extensive evaluation that demonstrates the benefits of using a varying number of teaching assistant models at different sizes.

📄 PDF Abstract BibTeX arXiv:2008.06814

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationModel Compression

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning

2022-10-14 · Donggeun Yoon, Jinsun Park, Donghyeon Cho

Recently, alpha matting has received a lot of attention because of its usefulness in mobile applications such as selfies. Therefore, there has been a demand for a lightweight alpha matting model due to the limited comput…

Image MattingSemantic Segmentation

Automated Channel Pruning with Learned Importance

2021-09-29 · Łukasz Treszczotko, Pawel Kubik

Neural network pruning allows for significant reduction of model size and latency. However, most of the current network pruning methods do not consider channel interdependencies and a lot of manual adjustments are requir…

DenoisingGPUImage DenoisingKnowledge Distillation+1

Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation

2025-10-17 · Fei Wang, Li Shen, Liang Ding, Chao Xue 외 arxiv

Large Language Models excel at natural language processing tasks, but their massive size leads to high computational and storage demands. Recent works have sought to reduce their model size through layer-wise structured …

Deep Neural Compression Via Concurrent Pruning and Self-Distillation

2021-09-30 · James O' Neill, Sourav Dutta, Haytham Assem

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational simila…

Knowledge DistillationLanguage ModelingLanguage Modelling

Class-Discriminative CNN Compression

2021-10-21 · Yuchen Liu, David Wentzlaff, S. Y. Kung

Compressing convolutional neural networks (CNNs) by pruning and distillation has received ever-increasing focus in the community. In particular, designing a class-discrimination based approach would be desired as it fits…