NAS-FCOS: Fast Neural Architecture Search for Object Detection

06/11/2019
by   Ning Wang, et al.
0

The success of deep neural networks relies on significant architecture engineering. Recently neural architecture search (NAS) has emerged as a promise to greatly reduce manual effort in network design by automatically searching for optimal architectures, although typically such algorithms need an excessive amount of computational resources, e.g., a few thousand GPU-days. To date, on challenging vision tasks such as object detection, NAS, especially fast versions of NAS, is less studied. Here we propose to search for the decoder structure of object detectors with search efficiency being taken into consideration. To be more specific, we aim to efficiently search for the feature pyramid network (FPN) as well as the prediction head of a simple anchor-free object detector, namely FCOS [20], using a tailored reinforcement learning paradigm. With carefully designed search space, search algorithms and strategies for evaluating network quality, we are able to efficiently search more than 2, 000 architectures in around 30 GPU-days. The discovered architecture surpasses state-of-the-art object detection models (such as Faster R-CNN, RetinaNet and FCOS) by 1 to 1.9 points in AP on the COCO dataset, with comparable computation complexity and memory footprint, demonstrating the efficacy of the proposed NAS for object detection.

READ FULL TEXT
research
04/16/2019

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

Current state-of-the-art convolutional architectures for object detectio...
research
12/24/2019

Computation Reallocation for Object Detection

The allocation of computation resources in the backbone is a crucial iss...
research
07/23/2020

Representation Sharing for Fast Object Detector Search and Beyond

Region Proposal Network (RPN) provides strong support for handling the s...
research
03/08/2021

OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

Recently, neural architecture search (NAS) has been exploited to design ...
research
03/21/2022

EAutoDet: Efficient Architecture Search for Object Detection

Training CNN for detection is time-consuming due to the large dataset an...
research
04/09/2021

TaylorMade VDD: Domain-adaptive Visual Defect Detector for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects

Visual defect detection (VDD) for high-mix low-volume production of non-...
research
12/02/2019

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

Despite the blooming success of architecture search for vision tasks in ...

Please sign up or login with your details

Forgot password? Click here to reset