Spatial reasoning for few-shot object detection

Geonuk Kim, Hong Gyu Jung, Seong Whan Lee

Research output: Contribution to journalArticlepeer-review

Abstract

Although modern object detectors rely heavily on a significant amount of training data, humans can easily detect novel objects using a few training examples. The mechanism of the human visual system is to interpret spatial relationships among various objects and this process enables us to exploit contextual information by considering the co-occurrence of objects. Thus, we propose a spatial reasoning framework that detects novel objects with only a few training examples in a context. We infer geometric relatedness between novel and base RoIs (Region-of-Interests) to enhance the feature representation of novel categories using an object detector well trained on base categories. We employ a graph convolutional network as the RoIs and their relatedness are defined as nodes and edges, respectively. Furthermore, we present spatial data augmentation to overcome the few-shot environment where all objects and bounding boxes in an image are resized randomly. Using the PASCAL VOC and MS COCO datasets, we demonstrate that the proposed method significantly outperforms the state-of-the-art methods and verify its efficacy through extensive ablation studies.

Original languageEnglish
Article number108118
JournalPattern Recognition
Volume120
DOIs
Publication statusPublished - 2021 Dec

Keywords

  • Data augmentation
  • Few-shot learning
  • Object detection
  • Transfer learning
  • Visual reasoning

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Spatial reasoning for few-shot object detection'. Together they form a unique fingerprint.

Cite this