Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks

TL;DR

The Inside-Outside Net (ION) enhances object detection by integrating inside-region multi-scale features with outside-region contextual information using skip pooling and recurrent neural networks, achieving state-of-the-art results.

Contribution

This paper introduces ION, a novel object detection framework that combines inside and outside contextual information with multi-scale features, improving detection accuracy.

Findings

Improves PASCAL VOC 2012 mAP from 73.9% to 76.4%.

Raises MS COCO mAP from 19.7% to 33.1%.

Won Best Student Entry at MS COCO Detection Challenge.

Abstract

It is well known that contextual and multi-scale representations are important for accurate visual recognition. In this paper we present the Inside-Outside Net (ION), an object 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 extract 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 76.4% mAP. On the new and more challenging MS COCO dataset, we improve state-of-art-the from 19.7% to 33.1% mAP. In the 2015 MS COCO Detection Challenge, our ION model won the Best Student Entry and finished 3rd place overall. As intuition suggests, our detection results provide strong evidence that context and multi-scale representations improve small object detection.