The search functionality is under construction.
The search functionality is under construction.

Improved Head and Data Augmentation to Reduce Artifacts at Grid Boundaries in Object Detection

Shinji UCHINOURA, Takio KURITA

  • Full Text Views

    0

  • Cite this

Summary :

We investigated the influence of horizontal shifts of the input images for one stage object detection method. We found that the object detector class scores drop when the target object center is at the grid boundary. Many approaches have focused on reducing the aliasing effect of down-sampling to achieve shift-invariance. However, down-sampling does not completely solve this problem at the grid boundary; it is necessary to suppress the dispersion of features in pixels close to the grid boundary into adjacent grid cells. Therefore, this paper proposes two approaches focused on the grid boundary to improve this weak point of current object detection methods. One is the Sub-Grid Feature Extraction Module, in which the sub-grid features are added to the input of the classification head. The other is Grid-Aware Data Augmentation, where augmented data are generated by the grid-level shifts and are used in training. The effectiveness of the proposed approaches is demonstrated using the COCO validation set after applying the proposed method to the FCOS architecture.

Publication
IEICE TRANSACTIONS on Information Vol.E107-D No.1 pp.115-124
Publication Date
2024/01/01
Publicized
2023/10/23
Online ISSN
1745-1361
DOI
10.1587/transinf.2023EDP7079
Type of Manuscript
PAPER
Category
Image Recognition, Computer Vision

Authors

Shinji UCHINOURA
  from Hiroshima University
Takio KURITA
  from Hiroshima University

Keyword