LAUSR

Polarity Loss: Improving Visual-Semantic Alignment for Zero-Shot Detection.

Sign Up to like & get
recommendations!
1 Published in 2022 at "IEEE transactions on neural networks and learning systems"

DOI: 10.1109/tnnls.2022.3184821

Abstract: Conventional object detection models require large amounts of training data. In comparison, humans can recognize previously unseen objects by merely knowing their semantic description. To mimic similar behavior, zero-shot object detection (ZSD) aims to recognize… read more here.

Keywords: semantic alignment; visual semantic; polarity loss; detection ... See more keywords