TY - GEN
T1 - Few-Shot Object Detection via Knowledge Transfer
AU - Kim, Geonuk
AU - Jung, Hong Gyu
AU - Lee, Seong Whan
N1 - Funding Information:
This work was supported by Institute for Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No. 2017-0-01779, A machine learning and statistical inference framework for explainable artificial intelligence; No. 2019-0-01371, Development of brain-inspired AI with human-like intelligence; No. 2019-0-00079, Artificial Intelligence Graduate School Program(Korea University)).
Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/11
Y1 - 2020/10/11
N2 - Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize. It exposes the practical weakness of the object detectors. On the other hand, human can easily master new reasoning rules with only a few demonstrations using previously learned knowledge. In this paper, we introduce a few-shot object detection via knowledge transfer, which aims to detect objects from a few training examples. Central to our method is prototypical knowledge transfer with an attached meta-learner. The meta-learner takes support set images that include the few examples of the novel categories and base categories, and predicts prototypes that represent each category as a vector. Then, the prototypes reweight each RoI (Region-of-Interest) feature vector from a query image to remodels R-CNN predictor heads. To facilitate the remodeling process, we predict the prototypes under a graph structure, which propagates information of the correlated base categories to the novel categories with explicit guidance of prior knowledge that represents correlations among categories. Extensive experiments on the PASCAL VOC dataset verifies the effectiveness of the proposed method.
AB - Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize. It exposes the practical weakness of the object detectors. On the other hand, human can easily master new reasoning rules with only a few demonstrations using previously learned knowledge. In this paper, we introduce a few-shot object detection via knowledge transfer, which aims to detect objects from a few training examples. Central to our method is prototypical knowledge transfer with an attached meta-learner. The meta-learner takes support set images that include the few examples of the novel categories and base categories, and predicts prototypes that represent each category as a vector. Then, the prototypes reweight each RoI (Region-of-Interest) feature vector from a query image to remodels R-CNN predictor heads. To facilitate the remodeling process, we predict the prototypes under a graph structure, which propagates information of the correlated base categories to the novel categories with explicit guidance of prior knowledge that represents correlations among categories. Extensive experiments on the PASCAL VOC dataset verifies the effectiveness of the proposed method.
KW - few-shot learning
KW - knowledge transfer
KW - object detection
UR - http://www.scopus.com/inward/record.url?scp=85098854589&partnerID=8YFLogxK
U2 - 10.1109/SMC42975.2020.9283497
DO - 10.1109/SMC42975.2020.9283497
M3 - Conference contribution
AN - SCOPUS:85098854589
T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
SP - 3564
EP - 3569
BT - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
Y2 - 11 October 2020 through 14 October 2020
ER -