paper-with-me

홈 › Papers

MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices

2019-12-02 · CVPR 2020 6 · Bo Chen, Golnaz Ghiasi, Hanxiao Liu, Tsung-Yi Lin, Dmitry Kalenichenko, Hartwig Adams, Quoc V. Le

Despite the blooming success of architecture search for vision tasks in resource-constrained environments, the design of on-device object detection architectures have mostly been manual. The few automated search efforts are either centered around non-mobile-friendly search spaces or not guided by on-device latency. We propose MnasFPN, a mobile-friendly search space for the detection head, and combine it with latency-aware architecture search to produce efficient object detection models. The learned MnasFPN head, when paired with MobileNetV2 body, outperforms MobileNetV3+SSDLite by 1.8 mAP at similar latency on Pixel. It is also both 1.0 mAP more accurate and 10% faster than NAS-FPNLite. Ablation studies show that the majority of the performance gain comes from innovations in the search space. Further explorations reveal an interesting coupling between the search space design and the search algorithm, and that the complexity of MnasFPN search space may be at a local optimum.

📄 PDF Abstract BibTeX arXiv:1912.01106

Code (2)

tensorflow/models 공식 구현 tf
tensorflow/models/tree/master/research/object_detection tf

Tasks

object-detectionObject Detection

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Entropy Regularization 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Neural Architecture Search Neural Architecture Search (NAS) learns a modular architecture which can be transferred from a small dataset to a large dataset. The method does this by reducing the problem…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

2020-04-30 · CVPR 2021 1 · Yunyang Xiong, Hanxiao Liu, Suyog Gupta, Berkin Akin 외

Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In this work, we investigate the optimalit…

CPUGPUNeural Architecture SearchObject+2

Adaptive Linear Span Network for Object Skeleton Detection

2020-11-08 · Chang Liu, Yunjie Tian, Jianbin Jiao, Qixiang Ye

Conventional networks for object skeleton detection are usually hand-crafted. Although effective, they require intensive priori knowledge to configure representative features for objects in different scale granularity.In…

Edge DetectionNeural Architecture SearchObjectObject Skeleton Detection

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

2019-04-16 · CVPR 2019 6 · Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang, Quoc V. Le

Current state-of-the-art convolutional architectures for object detection are manually designed. Here we aim to learn a better architecture of feature pyramid network for object detection. We adopt Neural Architecture Se…

Neural Architecture SearchObjectobject-detectionObject Detection+1

MFPN: A Novel Mixture Feature Pyramid Network of Multiple Architectures for Object Detection

2019-12-20 · Ting-Ting Liang, Yongtao Wang, Qijie Zhao, huan zhang 외

Feature pyramids are widely exploited in many detectors to solve the scale variation problem for object detection. In this paper, we first investigate the Feature Pyramid Network (FPN) architectures and briefly categoriz…

object-detectionObject Detection

Tech Report: One-stage Lightweight Object Detectors

2022-10-31 · Deokki Hong

This work is for designing one-stage lightweight detectors which perform well in terms of mAP and latency. With baseline models each of which targets on GPU and CPU respectively, various operations are applied instead of…

CPUGPUObjectobject-detection+1