A single model trained on 800 categories can detect objects from 200 unseen categories using only a few support images, without fine-tuning, and outperforms prior few-shot detectors on ImageNet Detection and MS COCO.
Optimization as a model for few-shot learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
A single model trained on 800 categories can detect objects from 200 unseen categories using only a few support images, without fine-tuning, and outperforms prior few-shot detectors on ImageNet Detection and MS COCO.