Can I read Few-shot Weakly-Supervised Object Detection via Directional Statistics on EtoBox?

Few-shot Weakly-Supervised Object Detection via Directional Statistics by Shaban, Amirreza; Rahimi, Amir; Ajanthan, Thalaiyasingam; Boots, Byron; Hartley, Richard is a scholarly article available to read on EtoBox.

What is Few-shot Weakly-Supervised Object Detection via Directional Statistics about?

Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object categories which limits their applicability in real world scenarios such as field robotics. In this work, we propose a probabilistic multiple instance learning approach for few-shot Common Object Localization (COL) and few-shot Weakly Supervised Object Detection (WSOD). In these tasks, only image-level labels, which are much cheaper to acquire, are available. We find that operating on features extracted from the last layer of a pre-trained Faster-RCNN is more effective compared to previous episodic learning based few-shot COL methods. Our model simultaneously learns the distribution of the novel objects and localizes them via expectation-maximization steps. As a probabilistic model, we employ von Mises-Fisher (vMF) distribution which captures the semantic information better than Gaussian distribution when applied to the pre-trained embedding space. When the novel objects are localized, we utilize them to learn a linear appearance model to detect novel classes in new images. Our extensive experiments show

Author

Shaban, Amirreza; Rahimi, Amir; Ajanthan, Thalaiyasingam; Boots, Byron; Hartley, Richard

Published

2021

Language

EN