The DOI matches its Crossref record; 63 of the 64 references it cites were found in a registry or an index.
Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration
Open accessAbstract
Filter pruning has been widely applied to neural network compression and acceleration. Existing methods usually utilize pre-defined pruning criteria, such as Lp-norm, to prune unimportant filters. There are two major limitations to these methods. First, existing methods fail to consider the variety of filter distribution across layers. To extract features of the coarse level to the fine level, the filters of different layers have various distributions. Therefore, it is not suitable to utilize the same pruning criteria to different functional layers. Second, prevailing layer-by-layer pruning methods process each layer independently and sequentially, failing to consider that all the layers in the network collaboratively make the final prediction. In this paper, we propose Learning Filter Pruning Criteria (LFPC) to solve the above problems. Specifically, we develop a differentiable pruning criteria sampler. This sampler is learnable and optimized by the validation loss of the pruned network obtained from the sampled criteria. In this way, we could adaptively select the appropriate pruning criteria for different functional layers. Besides, when evaluating the sampled criteria, LFPC comprehensively consider the contribution of all the layers at the same time. Experiments validate our approach on three image classification benchmarks. Notably, on ILSVRC-2012, our LFPC reduces more than 60% FLOPs on ResNet-50 with only 0.83% top-5 accuracy loss.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Pruning is the well-studied topic in model compression and many methods have been proposed to advance the network pruning [103].”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [103]
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,889
(2017) · Cited by 11,625
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
Neural Architecture Search with Reinforcement LearningPreprint
Zoph, B., & Le, Q. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01578 · Cited by 5,705
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
Research works printed but not linked: 2
- carreira-perpinán, 0, learning-compression” algorithms for neural net pruning, CVPR
- han, 0, Learning both weights and connections for efficient neural network, NeurIPS
Cited by
Sorted by citations
Items 201–262 of 262
Pruning of the Object Detection Model Based on Multi-level Feature De-correlation
Xu, J., Liu, C., Qian, H., Zhu, Q., & Chen, J. (2025) · International Conference on Artificial Intelligence of Things and Computing (AITC) · doi:10.1145/3762329.3762371 · Cited by 1
Toward simplicity in dynamic inference: a critical study and redesign of early-exit networks
Addad, Y., Lechervy, A., & Jurie, F. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01748-y · Cited by 2
Dantas, M., Silva, M. L., Filho, A. T. D. O., Bezerra, D. D. F., Freitas, E., do Carmo, P. R. X., Sadok, D. F. H., Kelner, J., & Souza, R. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06916-1 · Cited by 1
Class-Discriminative CNN Compression
Liu, Y., Wentzlaff, D., & Kung, S. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956066 · Cited by 3
Block-Wisely Supervised Network Pruning with Knowledge Distillation and Markov Chain Monte Carlo
Liu, H., Du, F., Song, L., & Yu, Z. (2022) · Applied Sciences · doi:10.3390/app122110952 · Cited by 1
Improving pedestrian segmentation using region proposal-based CNN semantic segmentation
Lahgazi, M. J., Argoul, P., MAST-EMGCU, U. G. E., & Hakim, A. (2023) · Mathematical Modeling and Computing · doi:10.23939/mmc2023.03.854 · Cited by 1
Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks
Zhao, H., Zhou, T., Long, G., Jiang, J. B., & Chengqi Zhang, B. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43415-0_4 · Cited by 1
Edge intelligence: From deep learning's perspective
Liu, D., Kong, H., Luo, X., Huai, S., & Liu, W. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13812-6.00005-1 · Cited by 1
An analysis of different methods for deep neural network pruning
Gou, L., Han, Z., & Yuan, Z. (2024) · Applied and Computational Engineering · doi:10.54254/2755-2721/52/20241292 · Cited by 1
Pruning Networks Only Using Few-Shot Pretraining Based on Gradient Similarity Frequency
Hu, H., Zhang, H., Zhou, Q., & Chen, T. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3544582 · Cited by 2
Self-citationFeature Pruned and Weighted Convolutional Neural Network for Micro-Expression Recognition
Mohideen, A. K. (2025) · International Journal of Software Science and Computational Intelligence · doi:10.4018/ijssci.389197 · Cited by 1
Compressing Deep CNNs Using Basis Representation and Spectral Fine-Tuning
Tayyab, M. A., Khan, F. A., & Mahalanobis, A. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506128 · Cited by 1
Weight Evolution: Improving Deep Neural Networks Training through Evolving Inferior Weight Values
Lin, Z., Guo, K., Xing, X., & Xu, X. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475376 · Cited by 1
Evolving transferable neural pruning functions
Liu, Y., Kung, S., & Wentzlaff, D. (2022) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3512290.3528694 · Cited by 3
SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural NetworksPreprint
Zhu, B., Hofstee, H. P., Lee, J., & Al-Ars, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.05317 · Cited by 1
DNN Quantization with AttentionPreprint
Hacene, G. B., Mauch, L., Uhlich, S., & Cardinaux, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.13322 · Cited by 1
Evolving Transferable Pruning FunctionsPreprint
Liu, Y., Kung, S., & Wentzlaff, D. (2021) · arXiv (Cornell University) · Cited by 1
Improving image captioning methods using machine learning approaches
Atliha, V. (2023) · doi:10.20334/2023-021-m · Cited by 1
Search: A Self-Evolving Framework for Network Architecture OptimizationPreprint
Liang, Y., Xiang, D., & Li, X. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4761600 · Cited by 1
Coarse and fine-grained automatic cropping deep convolutional neural networkPreprint
Chang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.06379 · Cited by 1
DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning ProblemsPreprint
Gripon, V., Lassance, C., & Hacene, G. B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.01509
KCP: Kernel Cluster Pruning for Dense Labeling Neural NetworksPreprint
Yu, P.-H., Wu, S.-S., & Chen, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.06686
Al-Gabalawy, M. A. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22457
RetractedAIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural NetworksPreprint
Chang, J., Lu, Y., Xue, P., Xu, Y., & Wei, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.13591
Carrying out CNN Channel Pruning in a White BoxPreprint
Zhang, Y., Lin, M., Lin, C., Chen, J., Huang, F., Wu, Y., Tian, Y., & Ji, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.11883
Toward Efficient CNN Compression via Coordinate Descent Structure Search
Zhang, Y., & Ji, R. (2021) · IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) · doi:10.1109/tocs53301.2021.9688673
Linear Substitution Pruning: Consider All Filters Together
Liu, K., & Liu, C. (2022) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3532213.3532224
Attaining Class-Level Forgetting in Pretrained Model Using Few Samples
Singh, P. P., Mazumder, P., & Karim, M. A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19778-9_25
BiTAT: Neural Network Binarization with Task-Dependent Aggregated Transformation
Park, G., Yoon, J., Zhang, H., Zhang, X., Hwang, S. J., & Eldar, Y. C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25082-8_4 · Cited by 2
Self-citationClustering-Based Filter Pruning Approach for Efficient ConvNets
Khoche, D., & Naik, S. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-1699-3_5
Channel Regeneration: Improving Channel Utilization for Compact DNNs
Sharma, A. K., & Foroosh, H. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i2.25316
Soft Filter Independence Guided Filter PruningPreprint
Liu, Y., Gu, S., Shen, C., Zhao, X.-L., & Hu, Q. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4498131
Dynamic finegrained structured pruning sensitive to filter texture distribution
Li, P., Wang, Y., Wu, C., & Kang, X. (2023) · AI Communications · doi:10.3233/aic-230046
Using Model Optimization as Countermeasure against Model Recovery Attacks
Jap, D., & Bhasin, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-41181-6_11
Pse-Net: Channel Pruning for Convolutional Neural Networks with Parallel-Subnets EstimatorPreprint
Wang, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4673971
Group Regularization Learning with Dynamic Regularization Factor Based on BN Layer Scaling Factor
Li, B., Li, Z., & Li, F. (2023) · International Conference on New Trends in Computational Intelligence (NTCI) · doi:10.1109/ntci60157.2023.10403747
Network Pruning via Explicit Information Migration
Wu, J., Hu, D., & Zheng, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-981-99-9119-8_35
Shang, R., Zhu, S., Zhang, W., Xu, S., & Li, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4875115
Lightweight Detection Algorithm for Air-to-Ground Threat Object
Xu, X., Liu, B., Zhong, Y. F., & Hua, S. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2872/1/012032
Filter pruning via annealing decaying for deep convolutional neural networks acceleration
Huang, J., Xiong, L., Huang, X., Chen, Q., Jiang, N., & Huang, P. C. (2024) · Cluster Computing · doi:10.1007/s10586-024-04836-2
Global Static Pruning via Adaptive Sample Complexity Awareness
Ma, M., Wang, Y., Du, T., Gao, Q., Wang, Y., & Li, W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888955
Compressing Neural Networks on Limited Computing Resources
Lee, S., Lee, D., Hyun, M., Kim, H., & Song, B. C. (2025) · IEEE Access · doi:10.1109/access.2025.3567102
Kernel clustering-based deep model pruning for few category datasets
Huang, Y., Xie, J., Wang, K., & Wu, C. (2025) · Intelligent Data Analysis · doi:10.1177/1088467x251344924
Filter Pruning for Efficient CNNs via Adaptive Saliency Selection and Knowledge-Driven Hints
Lin, Z., Liu, H., & Pan, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9812-7_39
A New Channel Pruning Method Combining Lowrank Feature Optimization with Noise Adaptive
Jiang, Y., Quan, Y., Wang, Y., Jiang, Z. D., Liu, M., Liu, J., & Dong, F. (2025) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda65784.2025.11182627
A Survey of Deep Model Compression and Acceleration
Zhang, C., Liu, H., Wang, H., Wang, J., Zheng, S., Meng, X., & Zhu, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-1346-8_6
Multiscale Dynamic Inference Acceleration for Deep Neural Networks
Zhang, C., Liu, H., Wang, H., Du, W., Wang, J., & Zheng, S. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-2566-9_21
Tiny Titans: Efficient Large Vision, Language and Multimodal Models Through Pruning
Tavares, C. D. M., Mugnaini, L. G., do Nascimento, G. H., Pons, I., Ogawa, K., Stern, G., Libanio, L., Paes, A., Costa, A. H. R., & Jordão, A. (2025) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi67909.2025.11223371
Redundancy reduction with gradient-weighted pruning for cross-domain few-shot learning
Jia, J., Wei, S., Feng, X., & Yu, H. (2025) · CCF Transactions on High Performance Computing · doi:10.1007/s42514-025-00264-9
Wang, M. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3419
Hessian-driven N:M sparsity and quantization co-optimization for edge device deployment
Tang, M., Ling, M., Ren, M., Cai, Z., Liu, Z., Tang, S., & Li, J. (2025) · Integration · doi:10.1016/j.vlsi.2025.102629
Projective Pruning for Decoupling Weights
Chu, T., & Kovalenko, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06106-5_19
CSP: Channel and Space Pruning for Compressing Deep Convolutional Neural Networks
Li, Y., Wang, L., & Kuang, M. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3654455
Reconstruction and Consolidation Pruning with Feature Reload Mechanism for Efficient Deep CNNs
Zhang, L., Li, H., Guo, Z., Wang, J., Huang, X., Xie, J., Zhou, X., Zhou, L., & Lin, Y. (2026) · Symmetry · doi:10.3390/sym18040585
ADD: An Automated Neural Architecture Search Baseline for Deepfake Detection
Liu, P., Lin, Y., Liu, J., Wei, Y., & Zhou, J. T. (2025) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs66636.2025.00019
Self-citationInference acceleration and optimization in deep neural networks for computer vision
Keddous, F. E. (2022) · theses.fr (ABES) · doi:10.70675/b08b2f98z66c2z46d7za694z241b7296cbd2
MicroAI : embedded artificial intelligence for human activity recognition on smart glasses
Novac, P.-E. (2022) · theses.fr (ABES) · doi:10.70675/77c14a3ez0f87z4c4dza876z9064b1b107ec · Cited by 1
IPPKD: An Iterative Pruning method with Prompt Knowledge Distillation
Li, Y., Wang, L., & Tao, X. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114640
Efficient Pruning Optimization for Trainable Descriptor-Based Facade Signboard Classification
Samarin, A., Toropov, A., Nazarenko, A., Kotenko, E., Mamaeva, A., Nazarenko, D., Mikhailova, E., Malykh, V. A., Savelev, A., & Motyko, A. (2026) · Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct70069.2026.11506537
Analyzing spatiotemporal architectures in video classification: A deep dive into 3DCNNs
Pandya, D., & Rana, K. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21799-1
Liang, T., Du, L., & Lan, G. (2026) · Ad Hoc Networks · doi:10.1016/j.adhoc.2026.104406
Cho, C., Yun, S., Jun, J., Moon, S., & Ro, Y. (2026) · doi:10.1109/cvprf71909.2026.00720
Metadata
- Authors
- He, Y., Ding, Y., Liu, P., Zhu, L., Zhang, H., & Yang, Y.
- Affiliations
- University of Technology Sydney (AU)
- Baidu (China) (CN)
- Nanyang Technological University (SG)
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 2006-2015
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3035467254
- Cited by
- 262
- References
- 64
- Citations by year
- 2026: 9 · 2025: 35 · 2024: 43 · 2023: 62 · 2022: 55 · 2021: 49 · 2020: 9
- FWCI
- 13.50
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- OPUS - Open Publications of UTS Scholars (University of Technology Sydney) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- filter pruning, neural network compression, deep convolutional neural networks, layer-wise pruning, model acceleration, FLOPs reduction, image classification, ResNet50
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
