Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge
With the ever-increasing popularity of edge devices, it is necessary to implement real-time segmentation on the edge for autonomous driving and many other applications. Vision Transformers (ViTs) have shown considerably stronger results for many vision tasks. However, ViTs with the full-attention mechanism usually consume a large number of computational resources, leading to difficulties for real-time inference on edge devices. In this paper, we aim to derive ViTs with fewer computations and fast inference speed to facilitate the dense prediction of semantic segmentation on edge devices. To achieve this, we propose a pruning parameterization method to formulate the pruning problem of semantic segmentation. Then we adopt a bi-level optimization method to solve this problem with the help of implicit gradients. Our experimental results demonstrate that we can achieve 38.9 mIoU on ADE20K val with a speed of 56.5 FPS on Samsung S21, which is the highest mIoU under the same computation constraint with real-time inference.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization
Neural architecture search (NAS) and network pruning are widely studied efficient AI techniques, but not yet perfect. NAS performs exhaustive candidate architecture search, incurring tremendous search cost. Though (struc…
Instance SegmentationNetwork PruningNeural Architecture SearchSemantic SegmentationA One-Shot Reparameterization Method for Reducing the Loss of Tile Pruning on DNNs
Recently, tile pruning has been widely studied to accelerate the inference of deep neural networks (DNNs). However, we found that the loss due to tile pruning, which can eliminate important elements together with unimpor…
CAP-Context-Aware-Pruning-for-Semantic-Segmentation
Network pruning for deep convolutional neural networks (CNNs) has recently achieved notable research progress on image-level classification. However, most existing pruning methods are not catered to or evaluated on seman…
Network PruningSegmentationSemantic SegmentationCAP: Context-Aware Pruning for Semantic-Segmentation
Network pruning for deep convolutional neural networks (CNNs) has recently achieved notable research progress on image-level classification. However, most existing pruning methods are not catered to or evaluated on seman…
Network PruningSegmentationSemantic SegmentationDeep Neural Network Pruning for Nuclei Instance Segmentation in Hematoxylin & Eosin-Stained Histological Images
Recently, pruning deep neural networks (DNNs) has received a lot of attention for improving accuracy and generalization power, reducing network size, and increasing inference speed on specialized hardwares. Although prun…
Instance SegmentationMedical Image AnalysisNetwork Pruningregression+2