TY - GEN
T1 - Contrastive Class-Specific Encoding for Few-Shot Object Detection
AU - Lin, Dizhong
AU - Fu, Ying
AU - Wang, Xin
AU - Hu, Shu
AU - Zhu, Bin
AU - Song, Qi
AU - Wu, Xi
AU - Lyu, Siwei
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In this paper, we propose a new few-shot object detection (FSOD) framework that introduces a new contrastive branch to extract the class representation of images, which improves the generalization performance of the detection model for novel classes. Additionally, we investigate the effectiveness of both self-supervised and supervised contrastive losses for class-specific encoding in our framework. Experimental results on the benchmark datasets indicate that our proposed method archives the state-of-the-art performance compared with existing FSOD methods.
AB - In this paper, we propose a new few-shot object detection (FSOD) framework that introduces a new contrastive branch to extract the class representation of images, which improves the generalization performance of the detection model for novel classes. Additionally, we investigate the effectiveness of both self-supervised and supervised contrastive losses for class-specific encoding in our framework. Experimental results on the benchmark datasets indicate that our proposed method archives the state-of-the-art performance compared with existing FSOD methods.
KW - class-specific encoding
KW - contrastive learning
KW - few-shot object detector
KW - Object detection
UR - https://www.scopus.com/pages/publications/85137729944
U2 - 10.1109/ICME52920.2022.9859860
DO - 10.1109/ICME52920.2022.9859860
M3 - Conference contribution
AN - SCOPUS:85137729944
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
BT - ICME 2022 - IEEE International Conference on Multimedia and Expo 2022, Proceedings
PB - IEEE Computer Society
T2 - 2022 IEEE International Conference on Multimedia and Expo, ICME 2022
Y2 - 18 July 2022 through 22 July 2022
ER -