Curriculum Self-Paced Learning for Cross-Domain Object Detection

TL;DR

This paper introduces a simple, effective unsupervised self-paced learning algorithm for cross-domain object detection, improving results without additional inference overhead by learning from easy to hard target domain samples.

Contribution

It proposes a novel self-paced algorithm that leverages pseudo-labels for unsupervised domain adaptation, outperforming existing methods across multiple benchmarks.

Findings

Outperforms state-of-the-art on four benchmarks

Effective without inference overhead

Difficulty measure correlates well with performance

Abstract

Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e.g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN. On top of combining Cycle-GAN transformations and self-paced learning in a smart and efficient way, in this paper, we propose a novel self-paced algorithm that learns from easy to hard. Our method is simple and effective, without any overhead during inference. It uses only pseudo-labels for samples taken from the target domain, i.e. the domain adaptation is unsupervised. We conduct experiments on four cross-domain benchmarks, showing better results than the state of the art. We also perform an ablation study demonstrating the utility of each component in our framework. Additionally, we study the applicability of our framework to other object detectors. Furthermore, we compare our difficulty measure with other measures from the related literature, proving that it yields superior results and that it correlates well with the performance metric.