# Automatic adaptation of object detectors to new domains using self-training

## TL;DR

This paper presents a simple, effective method for unsupervised domain adaptation of object detectors by automatically generating labels through high-confidence detections and tracking, then retraining the model with a modified distillation loss.

## Contribution

It introduces a novel self-training approach using high-confidence detections and temporal cues, with a modified distillation loss for unsupervised domain adaptation of object detectors.

## Key findings

- Effective adaptation to surveillance and challenging scenarios
- Using tracking to obtain hard examples improves performance
- Soft-labels via distillation outperform hard-labels in adaptation

## Abstract

This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain labels on the target data by using high-confidence detections from the existing detector, augmented with hard (misclassified) examples acquired by exploiting temporal cues using a tracker. These automatically-obtained labels are then used for re-training the original model. A modified knowledge distillation loss is proposed, and we investigate several ways of assigning soft-labels to the training examples from the target domain. Our approach is empirically evaluated on challenging face and pedestrian detection tasks: a face detector trained on WIDER-Face, which consists of high-quality images crawled from the web, is adapted to a large-scale surveillance data set; a pedestrian detector trained on clear, daytime images from the BDD-100K driving data set is adapted to all other scenarios such as rainy, foggy, night-time. Our results demonstrate the usefulness of incorporating hard examples obtained from tracking, the advantage of using soft-labels via distillation loss versus hard-labels, and show promising performance as a simple method for unsupervised domain adaptation of object detectors, with minimal dependence on hyper-parameters.