A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning

TL;DR

This paper introduces a compact object detector head network that enhances feature interaction modeling and relational reasoning, leading to improved detection accuracy with fewer parameters.

Contribution

The proposed CODH effectively models implicit feature relationships and reduces model complexity, outperforming state-of-the-art methods in detection performance.

Findings

Parameter reduction by 40% compared to Cascade R-CNN

Performance improvement of 1.3% on COCO test-dev

Applicable to various multi-stage detectors

Abstract

Modeling implicit feature interaction patterns is of significant importance to object detection tasks. However, in the two-stage detectors, due to the excessive use of hand-crafted components, it is very difficult to reason about the implicit relationship of the instance features. To tackle this problem, we analyze three different levels of feature interaction relationships, namely, the dependency relationship between the cropped local features and global features, the feature autocorrelation within the instance, and the cross-correlation relationship between the instances. To this end, we propose a more compact object detector head network (CODH), which can not only preserve global context information and condense the information density, but also allows instance-wise feature enhancement and relational reasoning in a larger matrix space. Without bells and whistles, our method can effectively improve the detection performance while significantly reducing the parameters of the model, e.g., with our method, the parameters of the head network is 0.6 times smaller than the state-of-the-art Cascade R-CNN, yet the performance boost is 1.3% on COCO test-dev. Without losing generality, we can also build a more lighter head network for other multi-stage detectors by assembling our method.