Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction

TL;DR

This paper enhances object detection accuracy by combining Bayesian optimization for candidate region proposal and a structured loss for better localization, significantly outperforming previous methods on standard benchmarks.

Contribution

It introduces a novel combination of Bayesian optimization and structured loss training to improve CNN-based object detection localization.

Findings

Improved detection performance on PASCAL VOC 2007 and 2012 datasets.

Bayesian optimization effectively proposes candidate regions.

Structured loss explicitly penalizes localization errors.

Abstract

Object detection systems based on the deep convolutional neural network (CNN) have recently made ground- breaking advances on several object detection benchmarks. While the features learned by these high-capacity neural networks are discriminative for categorization, inaccurate localization is still a major source of error for detection. Building upon high-capacity CNN architectures, we address the localization problem by 1) using a search algorithm based on Bayesian optimization that sequentially proposes candidate regions for an object bounding box, and 2) training the CNN with a structured loss that explicitly penalizes the localization inaccuracy. In experiments, we demonstrated that each of the proposed methods improves the detection performance over the baseline method on PASCAL VOC 2007 and 2012 datasets. Furthermore, two methods are complementary and significantly outperform the previous state-of-the-art when combined.