Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner

TL;DR

This paper introduces A-NDFT, an improved domain-invariant object detection method that significantly reduces training time using feature replay and slow learner techniques, making it more practical for remote sensing applications.

Contribution

A-NDFT enhances NDFT by incorporating acceleration techniques, drastically reducing training time while preserving detection performance.

Findings

Training time reduced from 31 hours to 3 hours on UAVDT benchmark.

Maintains comparable detection accuracy with faster training.

Proposed methods are practical for large-scale remote sensing tasks.

Abstract

In deep learning-based object detection on remote sensing domain, nuisance factors, which affect observed variables while not affecting predictor variables, often matters because they cause domain changes. Previously, nuisance disentangled feature transformation (NDFT) was proposed to build domain-invariant feature extractor with with knowledge of nuisance factors. However, NDFT requires enormous time in a training phase, so it has been impractical. In this paper, we introduce our proposed method, A-NDFT, which is an improvement to NDFT. A-NDFT utilizes two acceleration techniques, feature replay and slow learner. Consequently, on a large-scale UAVDT benchmark, it is shown that our framework can reduce the training time of NDFT from 31 hours to 3 hours while still maintaining the performance. The code will be made publicly available online.