# DAP: Detection-Aware Pre-training with Weak Supervision

Source: [DAP: Detection-Aware Pre-training with Weak Supervision](<https://www.sota2.com/research/paper/68fa699b1e209131cea23063>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:04:46.235Z

Authors: Yuanyi Zhong, Jianfeng Wang, Lijuan Wang, Jian Peng, Yu-Xiong Wang, Lei Zhang

Published: 2021-03-30T19:48:30.000Z

## Abstract

This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks. In contrast to the widely used image classification-based pre-training (e.g., on ImageNet), which does not include any location-related training tasks, we transform a classification dataset into a detection dataset through a weakly supervised object localization method based on Class Activation Maps to directly pre-train a detector, making the pre-trained model location-aware and capable of predicting bounding boxes. We show that DAP can outperform the traditional classification pre-training in terms of both sample efficiency and convergence speed in downstream detection tasks including VOC and COCO. In particular, DAP boosts the detection accuracy by a large margin when the number of examples in the downstream task is small.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.16651>)

[PDF](<https://arxiv.org/pdf/2103.16651.pdf>)