Nicolas Gonthier, Saïd Ladjal and Yann Gousseau

PDF - Code - Dataset - Project - Journal

Abstract

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.

Keywords

• Deep learning
• Convolutional neural networks
• Weakly supervised object detection
• Non-photographic images
• Art analysis
• Multiple instance learning

Recommended citation: Gonthier, N., Ladjal S. and Gousseau Y. (2022). “Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts” Computer Vision and Image Understanding.