DETReg: Unsupervised Pretraining with Region Priors for Object Detection

TL;DR

DETReg is a novel self-supervised pretraining method for object detection that trains the entire detection network, including localization and embedding components, leading to improved performance especially in low-data scenarios.

Contribution

It introduces a comprehensive pretraining approach for the full detection architecture, integrating region priors and self-supervised embeddings, which was lacking in prior methods.

Findings

Improves detection performance on COCO, PASCAL VOC, and Airbus Ship benchmarks.

Enhances low-data and few-shot detection accuracy.

Outperforms competitive baselines in various settings.

Abstract

Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method that pretrains the entire object detection network, including the object localization and embedding components. During pretraining, DETReg predicts object localizations to match the localizations from an unsupervised region proposal generator and simultaneously aligns the corresponding feature embeddings with embeddings from a self-supervised image encoder. We implement DETReg using the DETR family of detectors and show that it improves over competitive baselines when finetuned on COCO, PASCAL VOC, and Airbus Ship benchmarks. In low-data regimes DETReg achieves improved performance, e.g., when training with only 1% of the labels and in the few-shot learning settings.