Hierarchical Head Design for Object Detectors

Shivang Agarwal (1) , Frédéric Jurie (1)

1 Equipe Image - Laboratoire GREYC - UMR6072

The notion of anchor plays a major role in modern detection algorithms such as the Faster-RCNN or the SSD detector. Anchors relate the features of the last layers of the detector with bounding boxes containing objects in images. Despite their importance, the literature on object detection has not paid real attention to them. The motivation of this paper comes from the observations that (i) each anchor learns to classify and regress candidate objects independently (ii) insufficient examples are available for each anchor in case of small-scale datasets. This paper addresses these questions by proposing a novel hierarchical head for the SSD detector. The new design has the added advantage of no extra weights, as compared to the original design at inference time, while improving detectors performance for small size training sets. Improved performance on PASCAL-VOC and state-of-the-art performance on FlickrLogos-47 validate the method. We also show when the proposed design does not give additional performance gain over the original design.

Mots clés: computer vision; object detection; 2D Object Detection; Computer Vision; Anchors; Deep Learning

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Shivang Agarwal, Frédéric Jurie. Hierarchical Head Design for Object Detectors. 2021. ⟨hal-03159588⟩