TY  - CONF
AU  - Sudeep Katakol
AU  - Luis Herranz
AU  - Fei Yang
AU  - Marta Mrak
A2  - CVPRW
PY  - 2021//
TI  - DANICE: Domain adaptation without forgetting in neural image compression
BT  - Conference on Computer Vision and Pattern Recognition Workshops
SP  - 1921
EP  - 1925
N2  - Neural image compression (NIC) is a new coding paradigm where coding capabilities are captured by deep models learned from data. This data-driven nature enables new potential functionalities. In this paper, we study the adaptability of codecs to custom domains of interest. We show that NIC codecs are transferable and that they can be adapted with relatively few target domain images. However, naive adaptation interferes with the solution optimized for the original source domain, resulting in forgetting the original coding capabilities in that domain, and may even break the compatibility with previously encoded bitstreams. Addressing these problems, we propose Codec Adaptation without Forgetting (CAwF), a framework that can avoid these problems by adding a small amount of custom parameters, where the source codec remains embedded and unchanged during the adaptation process. Experiments demonstrate its effectiveness and provide useful insights on the characteristics of catastrophic interference in NIC.
L1  - http://refbase.cvc.uab.es/files/KHY2021.pdf
UR  - http://dx.doi.org/10.1109/CVPRW53098.2021.00218
N1  - LAMP; 600.120; 600.141; 601.379
ID  - Sudeep Katakol2021
ER  -