Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts

08/03/2020 ∙ by Nicolas Gonthier, et al. ∙ 0

Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a simple multiple instance approach applied on pre-trained deep features yields excellent performances on non-photographic datasets, possibly including new classes. The approach does not include any fine-tuning or cross-domain learning and is therefore efficient and possibly applicable to arbitrary datasets and classes. We investigate several flavors of the proposed approach, some including multi-layers perceptron and polyhedral classifiers. Despite its simplicity, our method shows competitive results on a range of publicly available datasets, including paintings (People-Art, IconArt), watercolors, cliparts and comics and allows to quickly learn unseen visual categories.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 20

page 21

page 22

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.