Name: Vinicius Ferraço Arruda
Type: MSc dissertation
Publication date: 24/02/2022
Advisor:

Namesort descending Role
Thiago Oliveira dos Santos Advisor *

Examining board:

Namesort descending Role
Filipe Wall Mutz External Examiner *
Thiago Oliveira dos Santos Advisor *
Thomas Walter Rauber Internal Examiner *

Summary: Unsupervised domain adaptation for object detection addresses the adaptation of detectors
trained in a source domain to work accurately in an unseen target domain. In real-world
applications, object detectors are desired to work accurately regardless of the application
domain (e.g., weather condition). These models have the intrinsic property of being biased
towards the training data and are known to not generalize well to unseen data. The greatest
availability of datasets can be seen in the most prevalent domains (e.g., sunny day), but for
certain applications it may be necessary to train a model to deploy in a less prevalent one
(e.g., foggy day). In addition, the acquisition of a new dataset involves the laborious process
of data annotation, but collecting large amounts of data without annotation might be
feasible. Recently, methods for unsupervised domain adaptation approaching the alignment
of the intermediate features proven to be promising, achieving state-of-the-art results.
However, these methods are laborious to implement and hard to interpret. Although
promising, there is still room for improvements to close the performance gap toward the
upper-bound (when training with the target data). In this work, we propose a method
to generate an artificial dataset in the target domain to train an object detector. We
employed an unsupervised image translator (CycleGAN) and a neural style transfer method
(AdaIN-based) using only annotated data from the source domain and non-annotated data
from the target domain. Our key contributions are the proposal of a less complex yet more
effective method that also has an improved interpretability. Results on real-world scenarios
for autonomous driving show significant improvements, outperforming state-of-the-art
methods in most cases, further closing the gap toward the upper-bound.

Access to document

Acesso à informação
Transparência Pública

© 2013 Universidade Federal do Espírito Santo. Todos os direitos reservados.
Av. Fernando Ferrari, 514 - Goiabeiras, Vitória - ES | CEP 29075-910