GAIA: A Transfer Learning System of Object Detection that Fits Your Needs

Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently. However, as there exist numerous application scenarios that have distinctive demands such as certain latency constraints and specialized data distributions, it is prohibitively expensive to take advantage of large-scale pre-training for per-task requirements. In this paper, we focus on the area of object detection and present a transfer learning system named GAIA, which could automatically and efficiently give birth to customized solutions according to heterogeneous downstream needs. GAIA is capable of providing powerful pre-trained weights, selecting models that conform to downstream demands such as latency constraints and specified data domains, and collecting relevant data for practitioners who have very few datapoints for their tasks. With GAIA, we achieve promising results on COCO, Objects365, Open Images, Caltech, CityPersons, and UODB which is a collection of datasets including KITTI, VOC, WiderFace, DOTA, Clipart, Comic, and more. Taking COCO as an ex-ample, GAIA is able to efficiently produce models covering a wide range of latency from 16ms to 53ms, and yields AP from 38.2 to 46.5 without whistles and bells. To benefit every practitioner in the community of object detection, GAIA is released at https://github.com/GAIA-vision.

[1]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Quoc V. Le,et al.  BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models , 2020, ECCV.

[3]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Chuang Gan,et al.  Once for All: Train One Network and Specialize it for Efficient Deployment , 2019, ICLR.

[5]  Lucas Beyer,et al.  Big Transfer (BiT): General Visual Representation Learning , 2020, ECCV.

[6]  Shengcai Liao,et al.  Pedestrian Detection: The Elephant In The Room , 2020, ArXiv.

[7]  Yang Song,et al.  Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Mark Chen,et al.  Language Models are Few-Shot Learners , 2020, NeurIPS.

[9]  Ronald M. Summers,et al.  Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  知秀 柴田.  5分で分かる!? 有名論文ナナメ読み：Jacob Devlin et al. : BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding , 2020 .

[12]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[13]  Jian Sun,et al.  DetNAS: Backbone Search for Object Detection , 2019, NeurIPS.

[14]  Ying Wu,et al.  Object Detection with a Unified Label Space from Multiple Datasets , 2020, ECCV.

[15]  Tieniu Tan,et al.  Large-Scale Object Detection in the Wild From Imbalanced Multi-Labels , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Chen Sun,et al.  Revisiting Unreasonable Effectiveness of Data in Deep Learning Era , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[17]  Kiyoharu Aizawa,et al.  Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Bernt Schiele,et al.  CityPersons: A Diverse Dataset for Pedestrian Detection , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Quoc V. Le,et al.  NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Shuo Yang,et al.  WIDER FACE: A Face Detection Benchmark , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[23]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[24]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[25]  Jana Kosecka,et al.  Multiview RGB-D Dataset for Object Instance Detection , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[26]  Quoc V. Le,et al.  Understanding and Simplifying One-Shot Architecture Search , 2018, ICML.

[27]  Nuno Vasconcelos,et al.  Towards Universal Object Detection by Domain Attention , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Christian Szegedy,et al.  DeepPose: Human Pose Estimation via Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[30]  Ramesh Raskar,et al.  Designing Neural Network Architectures using Reinforcement Learning , 2016, ICLR.

[31]  Yunhong Wang,et al.  Receptive Field Block Net for Accurate and Fast Object Detection , 2017, ECCV.

[32]  Colin Raffel,et al.  Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer , 2019, J. Mach. Learn. Res..

[33]  Kaiming He,et al.  Exploring the Limits of Weakly Supervised Pretraining , 2018, ECCV.

[34]  Yiming Yang,et al.  DARTS: Differentiable Architecture Search , 2018, ICLR.

[35]  Kaiming He,et al.  Rethinking ImageNet Pre-Training , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[36]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[38]  Kilian Q. Weinberger,et al.  Deep Networks with Stochastic Depth , 2016, ECCV.

[39]  Vijay Vasudevan,et al.  Learning Transferable Architectures for Scalable Image Recognition , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Sanja Fidler,et al.  Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Roee Aharoni,et al.  Unsupervised Domain Clusters in Pretrained Language Models , 2020, ACL.

[43]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Yong Yu,et al.  Efficient Architecture Search by Network Transformation , 2017, AAAI.

[45]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[46]  M. Kendall.  A NEW MEASURE OF RANK CORRELATION , 1938 .

[47]  Kan Chen,et al.  Billion-scale semi-supervised learning for image classification , 2019, ArXiv.

[48]  Quoc V. Le,et al.  EfficientDet: Scalable and Efficient Object Detection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[49]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[50]  Tieniu Tan,et al.  Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection , 2019, NeurIPS.

[51]  Huajun Feng,et al.  Libra R-CNN: Towards Balanced Learning for Object Detection , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Quoc V. Le,et al.  Efficient Neural Architecture Search via Parameter Sharing , 2018, ICML.

[53]  Thomas B. Moeslund,et al.  Vision-Based Traffic Sign Detection and Analysis for Intelligent Driver Assistance Systems: Perspectives and Survey , 2012, IEEE Transactions on Intelligent Transportation Systems.

[54]  Song Han,et al.  ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware , 2018, ICLR.

[55]  Jordi Pont-Tuset,et al.  The Open Images Dataset V4 , 2018, International Journal of Computer Vision.

[56]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[57]  Thomas S. Huang,et al.  Universally Slimmable Networks and Improved Training Techniques , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[58]  Nuno Vasconcelos,et al.  Cascade R-CNN: Delving Into High Quality Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[59]  Jian Sun,et al.  Objects365: A Large-Scale, High-Quality Dataset for Object Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[60]  Yi Li,et al.  Deformable Convolutional Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[61]  Larry S. Davis,et al.  An Analysis of Pre-Training on Object Detection , 2019, ArXiv.

[62]  Petr Sojka,et al.  Software Framework for Topic Modelling with Large Corpora , 2010 .

[63]  Luc Van Gool,et al.  Domain Adaptive Faster R-CNN for Object Detection in the Wild , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[64]  Doug Downey,et al.  Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks , 2020, ACL.

[65]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[66]  Pietro Perona,et al.  Pedestrian Detection: An Evaluation of the State of the Art , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[67]  Jiebo Luo,et al.  DOTA: A Large-Scale Dataset for Object Detection in Aerial Images , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.