paper-with-me

홈 › Papers

Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge

2023-01-01 · CVPR 2023 1 · Changdi Yang, Pu Zhao, Yanyu Li, Wei Niu, Jiexiong Guan, Hao Tang, Minghai Qin, Bin Ren, Xue Lin, Yanzhi Wang

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization

2022-06-02 · Yanyu Li, Pu Zhao, Geng Yuan, Xue Lin 외

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 Segmentation

A One-Shot Reparameterization Method for Reducing the Loss of Tile Pruning on DNNs

2022-07-29 · Yanchen Li, Qingzhong Ai, Fumihiko Ino

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

2021-01-06 · wei he, Meiqing Wu, Mingfu Liang, Siew-Kei Lam

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 Segmentation

CAP: Context-Aware Pruning for Semantic-Segmentation

2021-01-06 · wei he, Meiqing Wu, Mingfu Liang, Siew-Kei Lam

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 Segmentation

Deep Neural Network Pruning for Nuclei Instance Segmentation in Hematoxylin & Eosin-Stained Histological Images

2022-06-15 · Amirreza Mahbod, Rahim Entezari, Isabella Ellinger, Olga Saukh

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