Color Constancy Convolutional Autoencoder

Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Jarno Nikkanen, Moncef Gabbouj

Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

5 Sitaatiot (Scopus)

Abstrakti

In this paper, we study the importance of pretraining for the generalization capability in the color constancy problem. We propose two novel approaches based on convolutional autoencoders: an unsupervised pre-training algorithm using a fine-tuned encoder and a semi-supervised pre-training algorithm using a novel composite-loss function. This enables us to solve the data scarcity problem and achieve competitive, to the state-of-the-art, results while requiring much fewer parameters on ColorChecker RECommended dataset. We further study the over-fitting phenomenon on the recently introduced version of INTEL-TUT Dataset for Camera Invariant Color Constancy Research, which has both field and non-field scenes acquired by three different camera models.

AlkuperäiskieliEnglanti
Otsikko2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019
KustantajaIEEE
Sivut1085-1090
Sivumäärä6
ISBN (elektroninen)9781728124858
ISBN (painettu)978-1-7281-2486-5
DOI - pysyväislinkit
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE Symposium Series on Computational Intelligence -
Kesto: 1 tammik. 1900 → …

Conference

ConferenceIEEE Symposium Series on Computational Intelligence
LyhennettäIEEE SSCI
Ajanjakso1/01/00 → …

Julkaisufoorumi-taso

  • Jufo-taso 1

!!ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Modelling and Simulation

Sormenjälki

Sukella tutkimusaiheisiin 'Color Constancy Convolutional Autoencoder'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä