A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks

Pikoulis, Erion Vasilis; Mavrokefalidis, Christos; Nousias, Stavros; Lalos, Aris S.

doi:10.1007/978-981-16-3357-7_5

Cited by 4 publications

(20 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [30], an efficient version of the YOLOv3 detector is obtained via a comprehensive pruning scheme including layer-level and channel-wise pruning, while light-weight image based detectors are also proposed in [31], via a combination of knowledge transfer and pruning strategies. Finally, [32] utilized a Dictionary Learning based vector quantization technique, for the acceleration of SqueezeDet and ResNetDet (both proposed in [14]) by roughly 60% and 70%, respectively, with negligible accuracy loss.…”

Section: B Model Compression and Acceleration In Automotive Applicationsmentioning

confidence: 99%

“…To this end, firstly, we focus on the state of the art VQ [35] and DL [32] based techniques that rely on the design of codebooks with a preset structure (in terms of their size, number of utilized codewords, etc.). By observing that such a structure limits their flexibility and adaptability on the problem at hand for achieving better acceleration and/or compression ratios, two novel extensions are proposed adding flexibility regarding the inherent trade-offs between compression (memory footprint) and acceleration (computational power) during the system design phase.…”

Section: Motivation and Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Accelerating Deep Neural Networks for Efficient Scene Understanding in Multi-Modal Automotive Applications

et al. 2023

View full text Add to dashboard Cite

Environment perception constitutes one of the most critical operations performed by semiand fully-autonomous vehicles. In recent years, Deep Neural Networks (DNNs) have become the standard tool for perception solutions owing to their impressive capabilities in analyzing and modelling complex and dynamic scenes, from (often muti-modal) sensory inputs. However, the well-established performance of DNNs comes at the cost of increased time and storage complexity, which may become problematic in automotive perception systems due to the requirement for a short prediction horizon (as in many cases inference must be performed in real time) and the limited computational, storage, and energy resources of mobile systems. A common way of addressing this problem is to transform the original large pretrained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques, improving both their storage and execution efficiency. Within the MCA framework, in this paper, we investigate the application of two state-of-the-art weight-sharing MCA techniques, namely a Vector Quantization (VQ) and a Dictionary Learning (DL) one, as well as two novel extensions, towards the acceleration and compression of widely used DNNs for 2D and 3D object-detection in automotive applications. Apart from the individual (uni-modal) networks, we also present and evaluate a multi-modal late-fusion algorithm for combining the detection results of the 2D and 3D detectors. Our evaluation studies are carried out on the KITTI Dataset. The obtained results lend themselves to a twofold interpretation. On the one hand, they showcase the significant acceleration and compression gains that can be achieved via the application of weight sharing on the selected DNN detectors, with limited accuracy loss, as well as highlight the performance differences between the two utilized weight sharing approaches. On the other, they demonstrate the substantial boost in detection performance obtained by combining the outcome of the two unimodal individual detectors, using the proposed late-fusion based multi-modal approach. Indeed, as our experiments have shown, pairing the high-performance DL-based MCA technique with the loss-mitigating effect of the multi-modal fusion approach, leads to highly accelerated models (up to approximately 2.5× and 6× for the 2D and 3D detectors, respectively) with the performance loss of the fused results ranging in most cases within single-digits figures (as low as around 1% for the class "cars").INDEX TERMS model compression and acceleration, multi-modal fusion, object detection, scene analysis, scene understanding, experimental evaluation I. INTRODUCTIONAutonomous vehicles (AV) are an integral part of the continuously evolving field of Intelligent Transportation Systems (ITS) [1], and introduce a variety of technical challenges intertwined with the levels of driving automation, as defined for example by the Society of Automobile Engineers (SAE) J3016 standard [2], ranging from "no driving automation" (level 0) to ...

show abstract

Section: B Model Compression and Acceleration In Automotive Applicationsmentioning

confidence: 99%

Section: Motivation and Contributionmentioning

confidence: 99%

Accelerating Deep Neural Networks for Efficient Scene Understanding in Multi-Modal Automotive Applications

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In this paper, we focus on weight sharing approaches. In particular, the highlights of the paper are as follows: (i) Two recently proposed weight sharing techniques [22], [23] are utilized on two well-known 3D point-cloud object detection frameworks, namely, PointPillars [9] and PV-RCNN [12]. (ii) The results obtained on the KITTI 3D object detection benchmark [5] reveal considerable acceleration gains, with limited accuracy loss, on both examined models.…”

Section: Contributionmentioning

confidence: 99%

“…However, treating the problem in a Dictionary Learning framework can lead to significant improvement over the conventional approach, as it was recently shown in works concerning both the acceleration of image classification DNNs (e.g. VGG, ResNet, SqueezeNet) [23], as well as for image-based object detectors (SqueezeDet and ResNetDet) [24].…”

Section: Weight Sharing Via Product Quantization On 3d Object Detecti...mentioning

confidence: 99%

“…where W and Γ are as in (1), D denotes the dictionary while Λ is a sparse matrix, with a hyperparameter controlling the sparsity of its columns. The main advantage of the DL-based codebook design first presented in [23], lies in its ability to significantly increase the size of the employed codebooks, without affecting the achieved acceleration, compared to conventional techniques. This is due to the decomposition of the codebook defined in (2), which decouples the size of the codebook from the number of operations it incurs.…”

Section: Weight Sharing Via Product Quantization On 3d Object Detecti...mentioning

confidence: 99%

See 1 more Smart Citation

Accelerating 3D scene analysis for autonomous driving on embedded AI computing platforms

Nousias

Pikoulis

Mavrokefalidis

et al. 2021

2021 IFIP/IEEE 29th International Conference on Very Large Scale Integration (VLSI-SoC)

Self Cite

View full text Add to dashboard Cite

The design of 3D object detection schemes that use point clouds as input in automotive applications has gained a lot of interest recently. Those schemes capitalize on Deep Neural Networks (DNNs) that have demonstrated impressive results in analyzing complex scenes. The proposed schemes are generally designed to improve the achieved performance, leading however to high performing approaches with high computational complexity. To mitigate this high complexity and to facilitate their deployment on edge devices, model compression and acceleration techniques can be utilized. In this paper, we propose compressed versions of two well-known 3D object detectors, namely, PointPillars and PV-RCNN, utilizing dictionary learning-based weight-sharing techniques. It is demonstrated that significant acceleration gains can be achieved with acceptable average precision loss when evaluated on the KITTI 3D object detection benchmark. These findings constitute a concrete step towards the deployment of high-performance networks in edge devices of limited resources, such as NVIDIA's Jetson TX2.

show abstract

Robust 4D awareness via diffusion adaptation over Connected and Autonomated vehicles

Piperigkos

Nousias

Lalos

2022

2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)

View full text Add to dashboard Cite

A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks

Cited by 4 publications

References 32 publications

Accelerating Deep Neural Networks for Efficient Scene Understanding in Multi-Modal Automotive Applications

Accelerating Deep Neural Networks for Efficient Scene Understanding in Multi-Modal Automotive Applications

Accelerating 3D scene analysis for autonomous driving on embedded AI computing platforms

Robust 4D awareness via diffusion adaptation over Connected and Autonomated vehicles

Contact Info

Product

Resources

About