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

04/15/2019
by   Aruni RoyChowdhury, et al.
16

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.

READ FULL TEXT

page 1

page 4

page 7

research
04/07/2019

Unsupervised Domain Adaptation for Multispectral Pedestrian Detection

Multimodal information (e.g., visible and thermal) can generate robust p...
research
08/13/2018

Unsupervised Hard Example Mining from Videos for Improved Object Detection

Important gains have recently been obtained in object detection by using...
research
03/09/2021

ST3D: Self-training for Unsupervised Domain Adaptation on 3D ObjectDetection

We present a new domain adaptive self-training pipeline, named ST3D, for...
research
05/23/2020

Self-Training for Domain Adaptive Scene Text Detection

Though deep learning based scene text detection has achieved great progr...
research
03/27/2023

Unsupervised Adaptation from Repeated Traversals for Autonomous Driving

For a self-driving car to operate reliably, its perceptual system must g...
research
08/04/2015

Online Domain Adaptation for Multi-Object Tracking

Automatically detecting, labeling, and tracking objects in videos depend...
research
08/08/2023

Toward unlabeled multi-view 3D pedestrian detection by generalizable AI: techniques and performance analysis

We unveil how generalizable AI can be used to improve multi-view 3D pede...

Please sign up or login with your details

Forgot password? Click here to reset