Multi-scale Volumes for Deep Object Detection and Localization

TL;DR

This paper introduces a multi-scale volume approach for deep object detection that enhances contextual understanding and improves detection and localization accuracy, especially for objects with large scale variation.

Contribution

The paper proposes a novel multi-scale volume framework operating on feature pyramids, outperforming single-scale methods in detection and localization tasks.

Findings

Significant improvements in detection performance on PASCAL VOC dataset.

Enhanced localization quality for small objects and large-scale variations.

Better detection of challenging object categories with scale diversity.

Abstract

This study aims to analyze the benefits of improved multi-scale reasoning for object detection and localization with deep convolutional neural networks. To that end, an efficient and general object detection framework which operates on scale volumes of a deep feature pyramid is proposed. In contrast to the proposed approach, most current state-of-the-art object detectors operate on a single-scale in training, while testing involves independent evaluation across scales. One benefit of the proposed approach is in better capturing of multi-scale contextual information, resulting in significant gains in both detection performance and localization quality of objects on the PASCAL VOC dataset and a multi-view highway vehicles dataset. The joint detection and localization scale-specific models are shown to especially benefit detection of challenging object categories which exhibit large scale variation as well as detection of small objects.