Skip to main navigation Skip to search Skip to main content

DEEP OBJECT DETECTION WITH EXAMPLE ATTRIBUTE BASED PREDICTION MODULATION

  • Harbin Institute of Technology Shenzhen
  • Shenzhen Key Laboratory of Visual Object Detection and Recognition
  • Peng Cheng Laboratory

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deep object detectors suffer from the gradient contribution imbalance during training. In this paper, we point out that such imbalance can be ascribed to the imbalance in example attributes, e.g., difficulty and shape variation degree. We further propose example attribute based prediction modulation (EAPM) to address it. In EAPM, first, the attribute of an example is defined by the prediction and the corresponding ground truth. Then, a modulating factor w.r.t the example attribute is introduced to modulate the prediction error. Finally, the new prediction and the ground-truth are input into the loss function. Essentially, we adjust the gradients of examples with specific attributes to reweight their contribution on the global gradients. We apply EAPM with focal loss and balanced L1 loss to simultaneously solve the imbalance in classification and localization. The experimental results on MS COCO demonstrate that EAPM can bring substantial improvement for deep object detectors.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2020-2024
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Externally publishedYes
Event2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 - Hybrid, Singapore
Duration: 22 May 202227 May 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityHybrid
Period22/05/2227/05/22

Keywords

  • Deep object detection
  • classification
  • example attribute
  • gradient contribution imbalance
  • localization

Fingerprint

Dive into the research topics of 'DEEP OBJECT DETECTION WITH EXAMPLE ATTRIBUTE BASED PREDICTION MODULATION'. Together they form a unique fingerprint.

Cite this