Condensing Two-stage Detection with Automatic Object Key Part Discovery

TL;DR

This paper introduces a method to condense two-stage object detection models by discovering key object parts, enabling significant parameter reduction with minimal accuracy loss.

Contribution

It proposes an automatic key part discovery task and a decomposition approach to reduce detection head parameters while maintaining performance.

Findings

Achieves around 50% parameter reduction with negligible accuracy loss.

Reduces parameters by up to 96% with only 1.5% performance drop.

Demonstrates effectiveness on popular detection datasets.

Abstract

Modern two-stage object detectors generally require excessively large models for their detection heads to achieve high accuracy. To address this problem, we propose that the model parameters of two-stage detection heads can be condensed and reduced by concentrating on object key parts. To this end, we first introduce an automatic object key part discovery task to make neural networks discover representative sub-parts in each foreground object. With these discovered key parts, we then decompose the object appearance modeling into a key part modeling process and a global modeling process for detection. Key part modeling encodes fine and detailed features from the discovered key parts, and global modeling encodes rough and holistic object characteristics. In practice, such decomposition allows us to significantly abridge model parameters without sacrificing much detection accuracy. Experiments on popular datasets illustrate that our proposed technique consistently maintains original performance while waiving around 50% of the model parameters of common two-stage detection heads, with the performance only deteriorating by 1.5% when waiving around 96% of the original model parameters. Codes are released on: https://github.com/zhechen/Condensing2stageDetection.