Self-Distillation: Towards Efficient and Compact Neural Networks
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
Remarkable achievements have been obtained by deep neural networks in the last several years. However, the breakthrough in neural networks accuracy is always accompanied by explosive growth of computation and parameters, which leads to a severe limitation of model deployment. In this paper, we propose a novel knowledge distillation technique named self-distillation to address this problem. Self-distillation attaches several attention modules and shallow classifiers at different depths of neural networks and distills knowledge from the deepest classifier to the shallower classifiers. Different from the conventional knowledge distillation methods where the knowledge of the teacher model is transferred to another student model, self-distillation can be considered as knowledge transfer in the same model - from the deeper layers to the shallow layers. Moreover, the additional classifiers in self-distillation allow the neural network to work in a dynamic manner, which leads to a much higher acceleration. Experiments demonstrate that self-distillation has consistent and significant effectiveness on various neural networks and datasets. On average, 3.49 and 2.32 percent accuracy boost are observed on CIFAR100 and ImageNet. Besides, experiments show that self-distillation can be combined with other model compression methods, including knowledge distillation, pruning and lightweight model design.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
CBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00140 · Cited by 9,708
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ma, N., Zhang, X., Zheng, H.-T., & Sun, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01264-9_8 · Cited by 7,356 · cited 2×
“Typical approaches include pruning [12], [13], [14], [15], [16], quantization [17], [18], [19], [20], light-weight neural network design [21], [22], [23], [24], [25], low rank factorization [26], [27] and knowledge distillation [28], [29], [30], [31].”
MethodZagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201 · cited 2×
“Typical approaches include pruning [12], [13], [14], [15], [16], quantization [17], [18], [19], [20], light-weight neural network design [21], [22], [23], [24], [25], low rank factorization [26], [27] and knowledge distillation [28], [29], [30], [31].”
MethodXNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408
FitNets: Hints for Thin Deep Nets
Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.6550 · Cited by 2,859
Buciluǎ, C., Caruana, R., & Niculescu-Mizil, A. (2006) · Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1150402.1150464 · Cited by 2,068
ResNeSt: Split-Attention Networks
Zhang, H., Wu, C., Zhang, Z., Zhu, Y., Lin, H., Zhang, Z., Sun, Y., He, T., Mueller, J., Manmatha, R., et al. (2020) · arXiv · doi:10.48550/arxiv.2004.08955 · Cited by 1,809 · cited 1×
“On the image classification task, the proposed self-distilla-tion is evaluated in two benchmark datasets: CIFAR100 [76] and ImageNet (ILSVRC2012) [77] and seven kinds of neural networks: ResNet [3], WideResNet [78], ResNeXt [4], SENet [79], ResNeSt [80] MobileNetV2 [22] and ShuffleNet [24].”
MethodThe Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Frankle, J., & Carbin, M. (2018) · arXiv · doi:10.48550/arxiv.1803.03635 · Cited by 1,529
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
Denton, R., Zaremba, W., Bruna, J., LeCun, Y., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1404.0736 · Cited by 1,414
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
He, Y., Lin, J., Liu, Z., Wang, H., Li, L.-J., & Han, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_48 · Cited by 1,400
Speeding up Convolutional Neural Networks with Low Rank Expansions
Jaderberg, M., Vedaldi, A., & Zisserman, A. (2014) · Proceedings of the British Machine Vision Conference 2014 · doi:10.5244/c.28.88 · Cited by 1,164
AutoAugment: Learning Augmentation Policies from Data
Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., & Le, Q. V. (2018) · arXiv · doi:10.48550/arxiv.1805.09501 · Cited by 1,106
A Comprehensive Overhaul of Feature Distillation
Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., & Choi, J. Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00201 · Cited by 706
Cross Modal Distillation for Supervision Transfer
Gupta, S., Hoffman, J., & Malik, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.309 · Cited by 530 · cited 1×
“Gupta et al. propose the cross modal knowledge distillation, which guides neural networks training on unlabelled depth prediction and optical flow images with a teacher trained on labelled RGB images [50].”
BackgroundBlockDrop: Dynamic Inference Paths in Residual Networks
Wu, Z., Nagarajan, T., Kumar, A., Rennie, S., Davis, L. S., Grauman, K., & Feris, R. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00919 · Cited by 465
Unifying distillation and privileged information
Lopez-Paz, D., Bottou, L., Schölkopf, B., & Vapnik, V. (2015) · arXiv · doi:10.48550/arxiv.1511.03643 · Cited by 270 · cited 1×
“David et al. unify the knowledge distillation with privileged information [53], [54].”
BackgroundImproved Knowledge Distillation via Teacher Assistant
Mirzadeh, S. I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., & Ghasemzadeh, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5963 · Cited by 101 · cited 3×
“Recently, researchers find that the choice of teacher models has a great impact on the accuracy of student models and the teacher with the highest accuracy is not the best teacher for distillation [32], [33], [34].”
BackgroundMethod
Cited by
Uncertainty-aware genomic deep learning with knowledge distillation
Zhou, J., Rizzo, K., Christensen, T., Tang, Z., & Koo, P. K. (2024) · doi:10.1101/2024.11.13.623485 · Cited by 14
“A related approach to DEGU is self-distillation [68], where the distillation process is carried out sequentially in an online manner.”
Verse: Virtual-gradient aware streaming lifelong learning with anytime inference
Banerjee, S., Verma, V. K., Mukherjee, A., Gupta, D., Namboodiri, V. P., & Rai, P. (2024) · 2024 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra57147.2024.10610702 · Cited by 3
Metadata
- Authors
- Zhang, L., Bao, C., & Ma, K.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2021
- Volume
- 44
- Issue
- 8
- Pages
- 1-1
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3137609883
- Cited by
- 228
- References
- 29
- FWCI
- 12.35
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.