Scalable, High-Quality Object Detection

TL;DR

This paper introduces a learning-based object proposal method, MSC-MultiBox, that achieves high-quality detection with efficient runtime, surpassing previous methods in accuracy and proposal recall on major datasets.

Contribution

The paper presents MSC-MultiBox, a data-driven approach that matches hand-engineered methods' performance while enabling efficient quality-runtime trade-offs in object detection.

Findings

Achieves 0.5 mAP on ILSVRC 2014 detection challenge with a single model.

Improves proposal AP from 0.42 to 0.53 over previous MultiBox.

Demonstrates better bounding-box recall with fewer proposals on COCO dataset.

Abstract

Current high-quality object detection approaches use the scheme of salience-based object proposal methods followed by post-classification using deep convolutional features. This spurred recent research in improving object proposal methods. However, domain agnostic proposal generation has the principal drawback that the proposals come unranked or with very weak ranking, making it hard to trade-off quality for running time. This raises the more fundamental question of whether high-quality proposal generation requires careful engineering or can be derived just from data alone. We demonstrate that learning-based proposal methods can effectively match the performance of hand-engineered methods while allowing for very efficient runtime-quality trade-offs. Using the multi-scale convolutional MultiBox (MSC-MultiBox) approach, we substantially advance the state-of-the-art on the ILSVRC 2014 detection challenge data set, with $0.5$ mAP for a single model and $0.52$ mAP for an ensemble of two models. MSC-Multibox significantly improves the proposal quality over its predecessor MultiBox~method: AP increases from $0.42$ to $0.53$ for the ILSVRC detection challenge. Finally, we demonstrate improved bounding-box recall compared to Multiscale Combinatorial Grouping with less proposals on the Microsoft-COCO data set.