paper-with-me

홈 › Papers

Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification

2019-10-01 · ICCV 2019 10 · Hang Xu, Lewei Yao, Wei Zhang, Xiaodan Liang, Zhenguo Li

Abstract Neural architecture search (NAS) has shown great potential in automating the manual process of designing a good CNN architecture for image classification. In this paper, we study NAS for object detection, a core computer vision task that classifies and localizes object instances in an image. Existing works focus on transferring the searched architecture from classification task (ImageNet) to the detector backbone, while the rest of the architecture of the detector remains unchanged. However, this pipeline is not task-specific or data-oriented network search which cannot guarantee optimal adaptation to any dataset. Therefore, we propose an architecture search framework named Auto-FPN specifically designed for detection beyond simply searching a classification backbone. Specifically, we propose two auto search modules for detection: Auto-fusion to search a better fusion of the multi-level features; Auto-head to search a better structure for classification and bounding-box(bbox) regression. Instead of searching for one repeatable cell structure, we relax the constraint and allow different cells. The search space of both modules covers many popular designs of detectors and allows efficient gradient-based architecture search with resource constraint (2 days for COCO on 8 GPU cards). Extensive experiments on Pascal VOC, COCO, BDD, VisualGenome and ADE demonstrate the effectiveness of the proposed method, e.g. achieving around 5% improvement than FPN in terms of mAP while requiring around 50% fewer parameters on the searched modules.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationGPUimage-classificationImage ClassificationNeural Architecture Searchobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 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 $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
FPN 설명 없음

Similar Papers 제목 키워드 기반

Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters

2022-06-17 · Harim Jung, Myeong-Seok Oh, Cheoljong Yang, Seong-Whan Lee

Most object detection frameworks use backbone architectures originally designed for image classification, conventionally with pre-trained parameters on ImageNet. However, image classification and object detection are ess…

Classificationimage-classificationImage ClassificationNeural Architecture Search+3

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

2021-04-09 · Kyosuke Tashiro, Koji Takeda, Kanji Tanaka, Tomoe Hiroki

Visual defect detection (VDD) for high-mix low-volume production of non-convex metal objects, such as high-pressure cylindrical piping joint parts (VDD-HPPPs), is challenging because subtle difference in domain (e.g., me…

Defect Detectionobject-detectionObject Detection

Automatic adaptation of object detectors to new domains using self-training

2019-04-15 · CVPR 2019 6 · Aruni RoyChowdhury, Prithvijit Chakrabarty, Ashish Singh, SouYoung Jin 외

This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain lab…

Domain AdaptationKnowledge DistillationPedestrian DetectionUnsupervised Domain Adaptation

Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video

2017-12-23 · Aljoša Ošep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers 외

We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform. We propose a fully automatic approach for object mining from video which builds upon a generic objec…

Autonomous DrivingClusteringObjectObject Discovery+1

Towards Railway Domain Adaptation for LiDAR-based 3D Detection: Road-to-Rail and Sim-to-Real via SynDRA-BBox

2025-07-22 · Xavier Diaz, Gianluca D'Amico, Raul Dominguez-Sanchez, Federico Nesti 외 arxiv

In recent years, interest in automatic train operations has significantly increased. To enable advanced functionalities, robust vision-based algorithms are essential for perceiving and understanding the surrounding envir…

3D Object DetectionDomain Adaptation