PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution

Liu, Zhijian; Tang, Haotian; Zhao, Shengyu; Shao, Kevin; Han, Song

doi:10.1109/tpami.2021.3109025

Cited by 21 publications

(14 citation statements)

References 84 publications

(119 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of point cloud processing, there are few works related to NAS or HO -to our knowledge, the issue of NAS has only been addressed a few times, e.g. [14]. However, the authors do not mention anything about working on a subset of the training set.…”

Section: B Selecting Dataset Subsetmentioning

confidence: 99%

PointPillars Backbone Type Selection for Fast and Accurate LiDAR Object Detection

Lis

Kryjak

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To address these challenges, one can check the effectiveness of different models by training on a subset of the original training set. In this paper, we present a comparison of three algorithms for selecting such a subsetrandom sampling, random per class sampling, and our proposed MONSPeC (Maximum Object Number Sampling per Class). We provide empirical evidence for the superior effectiveness of random per class sampling and MONSPeC over basic random sampling. By replacing random sampling with one of the more efficient algorithms, the results obtained on the subset are more likely to transfer to the results on the entire dataset. The code is available at: https://github.com/vision-agh/monspec.

show abstract

Section: B Selecting Dataset Subsetmentioning

confidence: 99%

PointPillars Backbone Type Selection for Fast and Accurate LiDAR Object Detection

Lis

Kryjak

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

show abstract

“…Another stream of research [44,9,45,42,43,21] focus on two-stage object detector design, which adds an RCNN network to existing one-stage object detectors. There are also U-Net like models specialized for 3D semantic segmentation [15,11,47,29,69], an important task for offline HD map construction.…”

Section: Related Workmentioning

confidence: 99%

BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

Liu¹,

Tang²,

Amini³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the Li-DAR point cloud with camera features. However, the camera-to-LiDAR projection throws away the semantic density of camera features, hindering the effectiveness of such methods, especially for semantic-oriented tasks (such as 3D scene segmentation). In this paper, we break this deeply-rooted convention with BEVFusion, an efficient and generic multi-task multi-sensor fusion framework. It unifies multimodal features in the shared bird's-eye view (BEV) representation space, which nicely preserves both geometric and semantic information. To achieve this, we diagnose and lift key efficiency bottlenecks in the view transformation with optimized BEV pooling, reducing latency by more than 40×. BEVFusion is fundamentally task-agnostic and seamlessly supports different 3D perception tasks with almost no architectural changes. It establishes the new state of the art on nuScenes, achieving 1.3% higher mAP and NDS on 3D object detection and 13.6% higher mIoU on BEV map segmentation, with 1.9× lower computation cost. * indicates equal contributions. The first two authors are listed in the alphabetical order.Preprint. Under review.

show abstract

“…Recently, Tang et al [198,281] propose 3D-NAS framework as a general tool to automatically design point cloud processing networks under resource constraints. The 3D-NAS framework supports different candidate networks with fine grained channel numbers, elastic network depth and resolution, allowing the #MACs of the subnets to span over a 16× range.…”

Section: Efficient Point Cloud Processingmentioning

confidence: 99%

Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications

Cai

Lin

et al. 2022

ACM Trans. Des. Autom. Electron. Syst.

Self Cite

View full text Add to dashboard Cite

Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing, and speech recognition. However, their superior performance comes at the considerable cost of computational complexity, which greatly hinders their applications in many resource-constrained devices, such as mobile phones and Internet of Things (IoT) devices. Therefore, methods and techniques that are able to lift the efficiency bottleneck while preserving the high accuracy of DNNs are in great demand to enable numerous edge AI applications. This article provides an overview of efficient deep learning methods, systems, and applications. We start from introducing popular model compression methods, including pruning, factorization, quantization, as well as compact model design. 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. We then cover efficient on-device training to enable user customization based on the local data on mobile devices. 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/token redundancy. Finally, to support all these algorithmic advancements, we introduce the efficient deep learning system design from both software and hardware perspectives.

show abstract

PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution

Cited by 21 publications

References 84 publications

PointPillars Backbone Type Selection for Fast and Accurate LiDAR Object Detection

PointPillars Backbone Type Selection for Fast and Accurate LiDAR Object Detection

BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications

Contact Info

Product

Resources

About