LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs
Recent advance in 2D CNNs has revealed that large kernels are important. However, when directly applying large convolutional kernels in 3D CNNs, severe difficulties are met, where those successful module designs in 2D become surprisingly ineffective on 3D networks, including the popular depth-wise convolution. To address this vital challenge, we instead propose the spatial-wise partition convolution and its large-kernel module. As a result, it avoids the optimization and efficiency issues of naive 3D large kernels. Our large-kernel 3D CNN network, LargeKernel3D, yields notable improvement in 3D tasks of semantic segmentation and object detection. It achieves 73.9% mIoU on the ScanNetv2 semantic segmentation and 72.8% NDS nuScenes object detection benchmarks, ranking 1st on the nuScenes LIDAR leaderboard. The performance further boosts to 74.2% NDS with a simple multi-modal fusion. In addition, LargeKernel3D can be scaled to 17x17x17 kernel size on Waymo 3D object detection. For the first time, we show that large kernels are feasible and essential for 3D visual tasks.
Code (2)
Tasks
3D Object DetectionObjectobject-detectionObject DetectionSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
Transformers have quickly shined in the computer vision world since the emergence of Vision Transformers (ViTs). The dominant role of convolutional neural networks (CNNs) seems to be challenged by increasingly effective …
Object DetectionSemantic SegmentationSparse-Complementary Convolution for Efficient Model Utilization on CNNs
We introduce an efficient way to increase the accuracy of convolution neural networks (CNNs) based on high model utilization without increasing any computational complexity. The proposed sparse-complementary convolution …
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead…
Image ClassificationScaling Continuous Kernels with Sparse Fourier Domain Learning
We address three key challenges in learning continuous kernel representations: computational efficiency, parameter efficiency, and spectral bias. Continuous kernels have shown significant potential, but their practical a…
Computational EfficiencySparse LearningScalingNet: extracting features from raw EEG data for emotion recognition
Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in a variety of tasks. Recently, CNNs based methods that are fed with hand-extracted EEG features gradually produce a powerful performa…
EEGElectroencephalogram (EEG)Emotion Recognition