Rethinking Classification and Localization for Object Detection

TL;DR

This paper analyzes the roles of fully connected and convolutional heads in object detection, revealing their task preferences, and proposes a double-head approach that improves detection accuracy on MS COCO.

Contribution

It provides a detailed understanding of head structures in object detection and introduces a double-head method that enhances performance by leveraging their complementary strengths.

Findings

Fully connected head excels in classification tasks.

Convolution head is better suited for localization.

Proposed double-head method improves AP by 3.5 and 2.8 on MS COCO.

Abstract

Two head structures (i.e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks. However, there is a lack of understanding of how does these two head structures work for these two tasks. To address this issue, we perform a thorough analysis and find an interesting fact that the two head structures have opposite preferences towards the two tasks. Specifically, the fully connected head (fc-head) is more suitable for the classification task, while the convolution head (conv-head) is more suitable for the localization task. Furthermore, we examine the output feature maps of both heads and find that fc-head has more spatial sensitivity than conv-head. Thus, fc-head has more capability to distinguish a complete object from part of an object, but is not robust to regress the whole object. Based upon these findings, we propose a Double-Head method, which has a fully connected head focusing on classification and a convolution head for bounding box regression. Without bells and whistles, our method gains +3.5 and +2.8 AP on MS COCO dataset from Feature Pyramid Network (FPN) baselines with ResNet-50 and ResNet-101 backbones, respectively.