A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Dynamic Network Quantization for Efficient Video Inference
[article]
2021
arXiv
pre-print
Preserved Fulltext
Motivated by the effectiveness of quantization for boosting efficiency, in this paper, we propose a dynamic network quantization framework, that selects optimal precision for each frame conditioned on ...
the input for efficient video recognition. ...
Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Disclaimer. ...
arXiv:2108.10394v1
fatcat:5gv2uwr6mfbdtku32g5slmgtia
Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. ...
network during inference for instant adaptation in different scenarios. ...
Despite recent progress in network quantization for improving efficiency of deep networks, most of the existing methods repeat the quantization process and retrain the low-precision network from scratch ...
arXiv:2103.01435v3
fatcat:qukv5qgpxjfxnixlor6blwfbi4
Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Though recognition accuracy is usually the first concern for new progresses, efficiency is actually rather important and sometimes critical for both academic research and industrial applications. ...
Moreover, insightful views on the opportunities and challenges of efficiency are also highly required for the entire community. ...
-
specific
Dynamic
No
Yes
No
Efficient Visual Recognition with Deep Neural NetworksImage Video PointFast Run-time Inference• Compact Networks (CNNs, RNNs, ..., NAS) • Tensor Decomposition (CP, ...
arXiv:2108.13055v2
fatcat:nf3lymdbvzgl7otl7gjkk5qitq
Editorial: Special Issue on Compact Deep Neural Networks With Industrial Applications
2020
IEEE Journal on Selected Topics in Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Shen et al. propose in "Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference" a framework for
dynamic inference on resource constrained hardware. ...
An application of computationally efficient neural networks for safety monitoring is described in "Computationally Efficient Spatio-Temporal Dynamic Texture Recognition for Volatile Organic Compound 1932 ...
doi:10.1109/jstsp.2020.3006323
fatcat:d75ni7ocajb4pemovq2l3ton4i
Implicit Neural Video Compression
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We further lower the bitrate by storing the network weights with learned integer quantization. ...
Together with a small residual network, this allows us to efficiently compress P-frames relative to the previous frame. ...
Quantization and training able local functional representations. arXiv preprint
of neural networks for efficient integer-arithmetic-only arXiv:2104.03960, 2021. 2, 4
inference ...
arXiv:2112.11312v1
fatcat:ogd256n4qzfc7epkankzy4ktuy
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
2022
ACM Transactions on Design Automation of Electronic Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2204.11786v1 fatcat:mm5ex4bkrbfwxkwmnbdjao6wky
Apart from general acceleration techniques, we also showcase several task-specific accelerations for point cloud, video, and natural language processing by exploiting their spatial sparsity and temporal ...
To reduce the large design cost of these manual solutions, we discuss the AutoML framework for each of them, such as neural architecture search (NAS) and automated pruning and quantization. ...
Tiny Video Networks [227] automatically design highly efficient models for video understanding. ...
doi:10.1145/3486618
fatcat:h6xwv2slo5eklift2fl24usine
Training for temporal sparsity in deep neural networks, application in video processing
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
On the other hand, temporal sparsity is an inherent feature of bio-inspired spiking neural networks (SNNs), which neuromorphic processing exploits for hardware efficiency. ...
Activation sparsity improves compute efficiency and resource utilization in sparsity-aware neural network accelerators. ...
., 2018] , the authors propose a novel DNN inference algorithm (AMS) alongside a DNN accelerator optimized for video-based inference. ...
arXiv:2107.07305v1
fatcat:zgkh4hmffndulpbymffq6vjmbq
Recurrent Residual Module for Fast Inference in Videos
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this work, we propose a framework called Recurrent Residual Module (RRM) to accelerate the CNN inference for video recognition tasks. ...
Deep convolutional neural networks (CNNs) have made impressive progress in many video recognition tasks such as video pose estimation and video object detection. ...
Efficient inference engine To implement the RRM framework efficiently, we utilize dynamic sparse matrix-vector multiplication(DSPMV) technique. ...
arXiv:1802.09723v1
fatcat:lap3sjz62rcibptwvphgq3bq2y
Efficient Integer-Arithmetic-Only Convolutional Neural Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We also experiment on VDSR for image super-resolution and on VRCNN for compression artifact reduction, both of which serve for regression tasks that natively require high inference accuracy. ...
However, previous works usually report a decline in the inference accuracy when converting well-trained floating-point-number (FPN) networks into integer networks. ...
Different from parameter quantization that quantizes static weights and biases into integer, activation quantization is dynamic as it quantizes the computed activations into integer during network inference ...
arXiv:2006.11735v1
fatcat:pw6br3es4beylbsediumduupsq
AET-EFN: A Versatile Design for Static and Dynamic Event-Based Vision
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Our method is also efficient and achieves the fastest inference speed among others. ...
dynamic scenes. ...
We also present a two-branch neural network design, the Event Frame Net (EFN), which is versatile for static and dynamic event-based vision. ...
arXiv:2103.11645v1
fatcat:g4mm3ugg7vclpfmtlxxwfupbpq
EMC2-NIPS 2019 Abstracts of Invited Talks
2019
2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This talk will uncover the need for building accurate, platform-specific power and latency models for convolutional neural networks (CNNs) and efficient hardware-aware CNN design methodologies, thus allowing ...
, computer vision, autonomous navigation/exploration and video/image processing. ...
We accelerate computation-intensive AI applications including (TSM) for efficient video recognition and PVCNN for efficient 3D recognition on point clouds. ...
doi:10.1109/emc2-nips53020.2019.00007
fatcat:bvtcsgwxsrh3bmwh6tba3ly3ra
Overview of the Neural Network Compression and Representation (NNR) Standard
2021
IEEE transactions on circuits and systems for video technology (Print)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Abstract-Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks (NNs). ...
The NNR standard contains compression-efficient quantization and deep context-adaptive binary arithmetic coding (DeepCABAC) as core encoding and decoding technologies, as well as neural network parameter ...
ACKNOWLEDGMENT The authors would like to thank the experts of ISO/IEC MPEG and in particular the MPEG NNR group for their contributions. ...
doi:10.1109/tcsvt.2021.3095970
fatcat:wl4tvtpjaveuxng6fqu4tost5y
Recurrent Residual Module for Fast Inference in Videos
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In this work, we propose a framework called Recurrent Residual Module (RRM) to accelerate the CNN inference for video recognition tasks. ...
Deep convolutional neural networks (CNNs) have made impressive progress in many video recognition tasks such as video pose estimation and video object detection. ...
Efficient inference engine To implement the RRM framework efficiently, we utilize dynamic sparse matrix-vector multiplication(DSPMV) technique. ...
doi:10.1109/cvpr.2018.00166
dblp:conf/cvpr/PanLFHZL18
fatcat:pc2z4kxacrcthckdljv2d6rcoy
A practical convolutional neural network as loop filter for intra frame
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
To ensure consistency, dynamic fixed points (DFP) are adopted in testing CNN. Parameters in the compressed model are first quantized to DFP and then used for inference of CNN. ...
First, different model is used for frames encoded with different quantization parameter (QP), respectively. It is expensive for hardware. ...
Before DFP inference, parameters in the compressed model are first quantized and converted to DFP. To recover performance loss due to quantization, fine-tuning is established [12] . ...
arXiv:1805.06121v1
fatcat:3kuhmvtotrd2plt3rn6r7qtb5q
ProgressiveNN: Achieving Computational Scalability with Dynamic Bit-Precision Adjustment by MSB-first Accumulative Computation
2021
International Journal of Networking and Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
BWB quantization decomposes and transforms each parameter into a bitwise format for ABS inference, which then utilizes the parameters in the most-significant-bit-first order, enabling progressive inference ...
This paper also presents a method to dynamically adjust the bit-precision of the ProgressiveNN to achieve a better trade-off between computational resource use and accuracy for practical applications using ...
For applications using sequential data such as audio and video, it is possible to determine proper computational cost based on previous inference results. ...
doi:10.15803/ijnc.11.2_338
fatcat:r5jmpw2vdfcgfhpevh6rr7oaza
« Previous
Showing results 1 — 15 out of 4,973 results