FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 7348 - 7358
• Main Authors: Sun, Bo, Li, Banghuai, Cai, Shengcai, Yuan, Ye, Zhang, Chi
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.01.2021
• Subjects: Benchmark testing; Encoding; Object detection; Pipelines; Power capacitors; Training; Visualization

Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the key to reach favorable few-shot learning performance. We observe object proposals...