MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
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 optimality of this design pattern over a broad range of mobile accelerators by revisiting the usefulness of regular convolutions. We discover that regular convolutions are a potent component to boost the latency-accuracy trade-off for object detection on accelerators, provided that they are placed strategically in the network via neural architecture search. By incorporating regular convolutions in the search space and directly optimizing the network architectures for object detection, we obtain a family of object detection models, MobileDets, that achieve state-of-the-art results across mobile accelerators. On the COCO object detection task, MobileDets outperform MobileNetV3+SSDLite by 1.7 mAP at comparable mobile CPU inference latencies. MobileDets also outperform MobileNetV2+SSDLite by 1.9 mAP on mobile CPUs, 3.7 mAP on Google EdgeTPU, 3.4 mAP on Qualcomm Hexagon DSP and 2.7 mAP on Nvidia Jetson GPU without increasing latency. Moreover, MobileDets are comparable with the state-of-the-art MnasFPN on mobile CPUs even without using the feature pyramid, and achieve better mAP scores on both EdgeTPUs and DSPs with up to 2x speedup. Code and models are available in the TensorFlow Object Detection API: https://github.com/tensorflow/models/tree/master/research/object_detection.
Code (4)
Tasks
CPUGPUNeural Architecture SearchObjectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Searching Toward Pareto-Optimal Device-Aware Neural Architectures
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for m…
image-classificationImage ClassificationSM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
The state-of-the-art object detection method is complicated with various modules such as backbone, feature fusion neck, RPN and RCNN head, where each module may have different designs and structures. How to leverage the …
GPUNeural Architecture SearchObjectobject-detection+1Detecting soccer balls with reduced neural networks: a comparison of multiple architectures under constrained hardware scenarios
Object detection techniques that achieve state-of-the-art detection accuracy employ convolutional neural networks, implemented to have optimal performance in graphics processing units. Some hardware systems, such as mobi…
Objectobject-detectionObject DetectionSearching for MobileNetV3
We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile phone CPUs through a combination of hardware-a…
ClassificationDecoderDichotomous Image SegmentationImage Classification+4SP-NAS: Serial-to-Parallel Backbone Search for Object Detection
Advanced object detectors usually adopt a backbone network designed and pretrained by ImageNet classification. Recently neural architecture search (NAS) has emerged to automatically design a task-specific backbone to bri…
General ClassificationNeural Architecture Searchobject-detectionObject Detection