Residual Features and Unified Prediction Network for Single Stage Detection

TL;DR

This paper introduces a novel single stage detection method that enhances feature map representation using residual blocks and deconvolution, coupled with a unified prediction module, achieving higher accuracy while maintaining fast computation.

Contribution

It proposes a new approach combining residual features and a unified prediction network to improve detection accuracy in single stage detectors.

Findings

Achieved higher detection scores than SSD on PASCAL VOC and MS COCO.

Maintained fast computation speed comparable to other single stage detectors.

Enhanced feature map representation for small object detection.

Abstract

Recently, a lot of single stage detectors using multi-scale features have been actively proposed. They are much faster than two stage detectors that use region proposal networks (RPN) without much degradation in the detection performances. However, the feature maps in the lower layers close to the input which are responsible for detecting small objects in a single stage detector have a problem of insufficient representation power because they are too shallow. There is also a structural contradiction that the feature maps have to deliver low-level information to next layers as well as contain high-level abstraction for prediction. In this paper, we propose a method to enrich the representation power of feature maps using Resblock and deconvolution layers. In addition, a unified prediction module is applied to generalize output results and boost earlier layers' representation power for prediction. The proposed method enables more precise prediction, which achieved higher score than SSD on PASCAL VOC and MS COCO. In addition, it maintains the advantage of fast computation of a single stage detector, which requires much less computation than other detectors with similar performance. Code is available at https://github.com/kmlee-snu/run