Abstract

It is well known that contextual and multi-scale repre-sentations are important for accurate visual recognition. In this paper we present the Inside-Outside Net (ION), anobject detector that exploits information both inside and outside the region of interest. Contextual information outside the region of interest is integrated using spatial recurrent neural networks. Inside, we use skip pooling to ex-tract information at multiple scales and levels of abstraction. Through extensive experiments we evaluate the design space and provide readers with an overview of what tricks of the trade are important. ION improves state-of-the-art on PASCAL VOC 2012 object detection from 73.9% to 77.9% mAP. On the new and more challenging MS COCO dataset, we improve state-of-the-art from 19.7% to 33.1% mAP. In the 2015 MS COCO Detection Challenge, our ION model won “Best Student Entry” and finished 3rd place overall. Asintuition suggests, our detection results provide strong evidence that context and multi-scale representations improve small object detection.