# Adapting Vehicle Detector to Target Domain by Adversarial Prediction Alignment

Source: [Adapting Vehicle Detector to Target Domain by Adversarial Prediction Alignment](<https://www.sota2.com/research/paper/68fa6a571e209131cea278fc>)

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

Data updated: 2025-10-25T23:22:37.170Z

Authors: Yohei Koga, Hiroyuki Miyazaki, Ryosuke Shibasaki

Published: 2021-07-06T06:21:39.000Z

## Abstract

While recent advancement of domain adaptation techniques is significant, most of methods only align a feature extractor and do not adapt a classifier to target domain, which would be a cause of performance degradation. We propose novel domain adaptation technique for object detection that aligns prediction output space. In addition to feature alignment, we aligned predictions of locations and class confidences of our vehicle detector for satellite images by adversarial training. The proposed method significantly improved AP score by over 5%, which shows effectivity of our method for object detection tasks in satellite images.

## 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/2107.02411>)

[PDF](<https://arxiv.org/pdf/2107.02411.pdf>)
