CoChat

DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition

Open access
Yang, Zhan, Raymond, Osolo Ian, Zhang, Chengyuan, Wan, Ying, Long, Jun · 2018 · IEEE Access
Cited by 48

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

Abstract

Deep convolutional neural networks (DCNNs) are currently popular in human activity recognition (HAR) applications. However, in the face of modern artificial intelligence sensor-based games, many research achievements cannot be practically applied on portable devices (i.e., smart phone, VR/AR). DCNNs are typically resource-intensive and too large to be deployed on portable devices, and thus, this limits the practical application of complex activity detection. In addition, since portable devices do not possess high-performance graphic processing units, there is hardly any improvement in Action Game (ACT) experience. Besides, in order to deal with multi-sensor collaboration, all previous HAR models typically treated the representations from different sensor signal sources equally. However, distinct types of activities should adopt different fusion strategies. In this paper, a novel scheme is proposed. This scheme is used to train 2-bit CNNs with weights and activations constrained to {-0.5, 0, 0.5}. It takes into account the correlation between different sensor signal sources and the activity types. This model, which we refer to as DFTerNet, aims at producing a more reliable inference and better trade-offs for practical applications. It is known that quantization of weights and activations can substantially reduce memory size and use more efficient bitwise operations to replace floating or matrix operations to achieve much faster calculation and lower power consumption. Our basic idea is to exploit quantization of weights and activations directly in pre-trained filter banks and adopt dynamic fusion strategies for different activity types. Experiments demonstrate that by using a dynamic fusion strategy, it is possible to exceed the baseline model performance by up to ~5% on activity recognition data sets, such as the OPPORTUNITY and PAMAP2 data sets. Using the quantization method proposed, we were able to achieve performances closer to that of the full-precision counterpart. These results were also verified using the UniMiB-SHAR data set. In addition, the proposed method can achieve ~9x acceleration on CPUs and ~11x memory saving.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/access.2018.2873315

Cites

19 of 19 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 19 references

Research works printed but not linked: 38

  1. zhou, 2017, Incremental network quantization Towards lossless cnns with low-precision weights
  2. hubara, 2016, Quantized neural networks Training neural networks with low precision weights and activations
  3. xu, 2015, Show, attend and tell: Neural image caption generation with visual attention, Proc Int Conf Mach Learn (ICML), 2048
  4. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  5. 10.3115/v1/D14-1181 · DOI · Paper page
  6. 10.1109/ACCESS.2018.2833888 · DOI
  7. 10.1049/el:19901121 · DOI
  8. 10.1109/ICCV.2015.522 · DOI · Paper page
  9. 10.1109/ACCESS.2017.2777003 · DOI
  10. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  11. cook, 2015, Activity Learning Discovering Recognizing and Predicting Human Behavior from Sensor Data
  12. 10.1145/2493988.2494349 · DOI · Paper page
  13. feldhorst, 2016, Motion classification for analyzing the order picking process using mobile sensors, Proc Int Conf Pattern Recognit Appl Methods, 706, 10.5220/0005828407060713 · DOI
  14. 10.1109/ICCI-CC.2015.7259385 · DOI · Paper page
  15. ioffe, 2015, Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift
  16. zeiler, 2012, ADADELTA An Adaptive Learning Rate Method
  17. simonyan, 2014, Very Deep Convolutional Networks for Large-scale Image Recognition
  18. wen, 2017, TernGrad: Ternary gradients to reduce communication in distributed deep learning, Proc Adv Neural Inf Process Syst (NIPS), 1508
  19. esser, 2016, Convolutional Networks for Fast Energy-Efficient Neuromorphic Computing
  20. han, 2015, Deep compression Compressing deep neural networks with pruning trained quantization and huffman coding
  21. courbariaux, 2015, BinaryConnect: Training deep neural networks with binary weights during propagations, Proc Adv Neural Inf Process Syst (NIPS), 3123
  22. courbariaux, 2016, Binarized neural networks Training deep neural networks with weights and activations constrained to +1 or ?1
  23. rastegari, 2016, Xnor-net Imagenet classification using binary convolutional neural networks
  24. 10.1109/FPT.2014.7082765 · doi:10.1109/fpt.2014.7082765
  25. 10.1145/3123021.3123046 · DOI · Paper page
  26. 10.1109/ACCESS.2016.2608777 · DOI
  27. 10.1109/ACCESS.2017.2770178 · DOI
  28. yang, 2015, Deep convolutional neural networks on multichannel time series for human activity recognition, Proc Intern Joint Conf Artificial Intel (IJCAI), 3995
  29. 10.1109/ACCESS.2018.2810264 · DOI
  30. horowitz, 2014, Computing’s energy problem (and what we can do about it), IEEE Int Solid-State Circuits Conf Dig Tech Papers, 10
  31. 10.1109/ACCESS.2017.2753830 · DOI
  32. mu?a, 2016, Faster Population Counts using AVX2 Instructions
  33. szegedy, 2016, Inception-v4 inception-resnet and the impact of residual connections on learning
  34. 10.1007/978-3-319-46484-8_48 · DOI · Paper page
  35. rueda, 2018, Learning attribute representation for human activity recognition
  36. alistarh, 2017, QSGD: Communication-efficient SGD via gradient quantization and encoding, Proc Adv Neural Inf Process Syst (NIPS), 1707
  37. 10.1007/BF02678430 · DOI · Paper page
  38. bengio, 2013, Estimating or propagating gradients through stochastic neurons

Cited by

See all 48

Metadata

Authors
Yang, Z., Raymond, O. I., Zhang, C., Wan, Y., & Long, J.
Venue
IEEE Access
Published
2018
Volume
6
Pages
56750-56764
ISSN
2169-3536 (ISSN-L)
OpenAlex
W2887355508
Cited by
48
References
19
FWCI
2.74
Type
journal article
Language
en
Open access
gold
Funders
  • National Natural Science Foundation of China (61472450)
  • Natural Science Foundation of Hunan Province (2017JJ3417)
  • Science and Technology Plan of Hunan (2016TP1003)

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition. https://app.cochat.ai/papers/10.1109/access.2018.2873315
The paper
Yang, Z., Raymond, O. I., Zhang, C., Wan, Y., & Long, J. (2018). DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition. IEEE Access. https://doi.org/10.1109/access.2018.2873315

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.