mlsanityData to 7 Oct 2026

FSD: Fully-Specialized Detector via Neural Architecture Search

arXiv 2305.16649 ↗First posted 26 May 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Most generic object detectors are mainly built for standard object detection tasks such as COCO and PASCAL VOC. They might not work well and/or efficiently on tasks of other domains consisting of images that are visually different from standard datasets. To this end, many advances have been focused on adapting a general-purposed object detector with limited domain-specific designs. However, designing a successful task-specific detector requires extraneous manual experiments and parameter tuning through trial and error. In this paper, we first propose and examine a fully-automatic pipeline to design a fully-specialized detector (FSD) which mainly incorporates a neural-architectural-searched model by exploring ideal network structures over the backbone and task-specific head. On the DeepLesion dataset, extensive results show that FSD can achieve 3.1 mAP gain while using approximately 40% fewer parameters on binary lesion detection task and improved the mAP by around 10% on multi-type lesion detection task via our region-aware graph modeling compared with existing general-purposed medical lesion detection networks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 42 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

33 of 42 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  12. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
21 more
  1. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  2. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  3. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  4. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  5. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  6. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  7. 2017Large-Scale Evolution of Image Classifierscited by 348
  8. 2017Relation Networks for Object Detectioncited by 305
  9. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  10. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
  11. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 258
  12. 2016Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learningcited by 209
  13. 2017Receptive Field Block Net for Accurate and Fast Object Detectioncited by 140
  14. 2018Searching for Efficient Multi-Scale Architectures for Dense Image Predictioncited by 96
  15. 2017Evolving Deep Neural Networkscited by 93
  16. 2020Few-shot Neural Architecture Searchcited by 50
  17. 2018Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detectioncited by 46
  18. 2017Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-scale Lesion Databasecited by 42
  19. 20183D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detectioncited by 24
  20. 2020MEBOW: Monocular Estimation of Body Orientation In the Wildcited by 14
  21. 2023Learning to Adapt to Online Streams with Distribution Shiftscited by 2

Built on by

Not cited yet.