Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects

Hila Levi (Weizmann Institue of Science), Shimon Ullman (Weizmann Institute of Science)

An image is not just a collection of objects, but rather a graph where each object is related to other objects through spatial and semantic relations. Using relational reasoning modules, such as the non-local module \cite{wang2017non}, can therefore improve object detection. Current schemes apply such dedicated modules either to a specific layer of the bottom-up stream, or between already-detected objects. We show that the relational process can be better modeled in a coarse-to-fine manner and present a novel framework, applying a non-local module sequentially to increasing resolution feature maps along the top-down stream. In this way, information can naturally passed from larger objects to smaller related ones. Applying the module to fine feature maps further allows the information to pass between the small objects themselves, exploiting repetitions of instances from of the same class. In practice, due to the expensive memory utilization of the non-local module, it is infeasible to apply the module as currently used to high-resolution feature maps. We redesigned the non local module, improved it in terms of memory and number of operations, allowing it to be placed anywhere along the network. We further incorporated relative spatial information into the module, in a manner that can be incorporated into our efficient implementation. We show the effectiveness of our scheme by improving the results of detecting small objects on COCO by 1-2 AP points over Faster and Mask RCNN and by 1 AP over using non-local module on the bottom-up stream.


Paper (PDF)
Supplementary material (ZIP)

title={Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects},
author={Hila Levi and Shimon Ullman},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Kirill Sidorov and Yulia Hicks},