Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner
This work addresses the impractical training times for domain adaptation in object detection, making it more feasible for applications like remote sensing, though it is incremental as it builds on prior NDFT methods.
The paper tackles the problem of slow training time in domain-invariant object detection for remote sensing by proposing A-NDFT, an improved method that reduces training time from 31 hours to 3 hours while maintaining performance on the UAVDT benchmark.
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.