Performance Guaranteed Network Acceleration via High-Order Residual Quantization
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Input binarization has shown to be an effective way for network acceleration. However, previous binarization scheme could be regarded as simple pixel-wise thresholding operations (i.e., order-one approximation) and suffers a big accuracy loss. In this paper, we propose a high-order binarization scheme, which achieves more accurate approximation while still possesses the advantage of binary operation. In particular, the proposed scheme recursively performs residual quantization and yields a series of binary input images with decreasing magnitude scales. Accordingly, we propose high-order binary filtering and gradient propagation operations for both forward and backward computations. Theoretical analysis shows approximation error guarantee property of proposed method. Extensive experimental results demonstrate that the proposed scheme yields great recognition accuracy while being accelerated.
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
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
XNOR-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
BinaryConnect: Training Deep Neural Networks with binary weights during propagations
Courbariaux, M., Bengio, Y., & David, J.-P. (2015) · arXiv · doi:10.48550/arxiv.1511.00363 · Cited by 2,180
Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., & Bengio, Y. (2016) · arXiv · doi:10.48550/arxiv.1602.02830 · Cited by 2,106
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
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 · cited 1×
“Methods in [22], [7] and [13] approximate a weight filter with a set of separable smaller filters.”
BackgroundSpeeding 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
Predicting Parameters in Deep Learning
Denil, M., Shakibi, B., Dinh, L., Ranzato, M., & de Freitas, N. (2013) · arXiv · doi:10.48550/arxiv.1306.0543 · Cited by 853 · cited 1×
“We divide these works into three categories: Parameter Pruning It is believed many deep learning models are over-parameterized with significant redundancy [6].”
BackgroundPredicting Parameters in Deep Learning
Shakibi, B. (2014) · University of British Columbia · doi:10.14288/1.0165555 · Cited by 462
Kim, M., & Smaragdis, P. (2016) · arXiv · doi:10.48550/arxiv.1601.06071 · Cited by 166 · cited 1×
“This Table shows the Test error rate of different binary method on MNIST: BEB (Binary expectation backpropagation [2]), BC (BinaryConnect [4]), BN (BinaryNet [5]), BNN (Bitwise Neural Networks [14]), XNOR (XNOR-Networks [21]), HORQ (This work).”
Method
Cited by
A Survey of Quantization Methods for Efficient Neural Network Inference
Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M. W., & Keutzer, K. (2022) · Low-Power Computer Vision · doi:10.1201/9781003162810-13 · Cited by 1,219
“…each branch, and we refer the interested readers to [191] for more details. a) Quantization Error Minimization: The first branch of solutions aims to minimize the quantization error, i.e., the gap between the real values and the quantized values [19, 34, 62, 102, 149, 155, 160, 165, 174, 211, 240].”
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
Zhang, D., Yang, J., Ye, D., & Hua, G. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01237-3_23 · Cited by 693
Binary Neural Networks: A Survey
Qin, H., Gong, R., Liu, X., Bai, X., Song, J., & Sebe, N. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107281 · Cited by 546
“J(b, α) = ‖x− αb‖(2) α∗,b∗ = arg min α,b J(b, α) S - XNOR-Net [58] RB+RP A - DoReFa-Net [60] A - High-Order Residual Quantization [70] A - ABC-Net [71] S - Two-Step Quantization [72] RB - - Binary Weight Networks via Hashing[73] S - PArameterized Clipping acTivation [74] A - LQ-Nets [61] RB - - Wide Reduced-Precision…”
MethodAutoregressive Image Generation using Residual Quantization
Lee, D., Kim, C., Kim, S., Cho, M., & Han, W.-S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01123 · Cited by 445
Low-bit Quantization of Neural Networks for Efficient Inference
Choukroun, Y., Kravchik, E., Yang, F., & Kisilev, P. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00363 · Cited by 404
“[24] proposed a high order quantization scheme of weights where the approximation residual is further processed allowing better refinement of full precision input.”
Background
Metadata
- Authors
- Li, Z., Ni, B., Zhang, W., Yang, X., & Gao, W.
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 2603-2611
- OpenAlex
- W2963681088
- Cited by
- 102
- References
- 13
- FWCI
- 3.56
- Type
- conference paper
- Language
- en
- Open access
- green
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.