Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 1, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Assemble new object detector with few examples.

Kuiyuan Yang1, Meng Wang, Xian-Sheng Hua

  • 1Department of Automation, the University of Science and Technology of China, Hefei 230027, China.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|June 3, 2011
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Improving Video Instance Segmentation via Temporal Pyramid Routing.

IEEE transactions on pattern analysis and machine intelligence·2022
Same author

Global Aggregation Then Local Distribution for Scene Parsing.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021
Same author

Towards Efficient Scene Understanding via Squeeze Reasoning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021
Same author

Nomogram Including Elastography for Prediction of Contralateral Central Lymph Node Metastasis in Solitary Papillary Thyroid Carcinoma Preoperatively.

Cancer management and research·2020
Same author

Category-Aware Spatial Constraint for Weakly Supervised Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019
Same author

Balanced Decoupled Spatial Convolution for CNNs.

IEEE transactions on neural networks and learning systems·2019
Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Semantic Frame Interpolation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

Limited training data degrades object detector performance. This study proposes using related auxiliary detectors to learn robust object detection with few examples by mining object relationships.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Object detection models typically require extensive training data to achieve satisfactory performance.
  • Limited training examples severely degrade the performance of object detectors.
  • Existing methods struggle with data scarcity for specific object categories.

Purpose of the Study:

  • To address the challenge of training effective object detectors with limited data.
  • To propose a novel approach leveraging auxiliary detectors for data-scarce object detection.
  • To improve the robustness and performance of object detectors when training examples are scarce.

Main Methods:

  • Exploiting a set of pre-trained auxiliary detectors trained on different object categories.

Related Experiment Videos

Last Updated: Jun 1, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • Mining global and local relationships between target and auxiliary object categories.
  • Adopting the deformable part model and exploring root and part filters from auxiliary detectors.
  • Utilizing an iterative solution guided by few target object training examples.

    • Main Results:

    • Demonstrated that relationships between object categories can be mined effectively.
    • Showcased the ability to learn a robust detector with very few training examples.
    • Achieved encouraging performance on the PASCAL VOC 2007 challenge dataset.
    • Validated the effectiveness of assembling a detector from related auxiliary detectors.

    Conclusions:

    • The proposed method successfully overcomes the limitations of insufficient training data for object detection.
    • Leveraging auxiliary detectors and their relationships offers a viable solution for data-scarce scenarios.
    • The approach shows significant promise for improving object detection in real-world applications with limited annotated data.