ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

GAN-tree: An incrementally learned hierarchical generative framework for multi-modal data distributions

Kundu, JN and Gor, M and Agrawal, D and Radhakrishnan, VB (2019) GAN-tree: An incrementally learned hierarchical generative framework for multi-modal data distributions. In: International Conference on Computer Vision, 27 Oct-2 Nov 2019, Seoul South Korea, pp. 8190-8199.

pro_iee_int_con_com_vis_2019O_8190-8199_2019.pdf - Published Version

Download (8MB) | Preview
Official URL: https://doi.org/10.1109/ICCV.2019.00828


Despite the remarkable success of generative adversarial networks, their performance seems less impressive for diverse training sets, requiring learning of discontinuous mapping functions. Though multi-mode prior or multi-generator models have been proposed to alleviate this problem, such approaches may fail depending on the empirically chosen initial mode components. In contrast to such bottom-up approaches, we present GAN-Tree, which follows a hierarchical divisive strategy to address such discontinuous multi-modal data. Devoid of any assumption on the number of modes, GAN-Tree utilizes a novel mode-splitting algorithm to effectively split the parent mode to semantically cohesive children modes, facilitating unsupervised clustering. Further, it also enables incremental addition of new data modes to an already trained GAN-Tree, by updating only a single branch of the tree structure. As compared to prior approaches, the proposed framework offers a higher degree of flexibility in choosing a large variety of mutually exclusive and exhaustive tree nodes called GAN-Set. Extensive experiments on synthetic and natural image datasets including ImageNet demonstrate the superiority of GAN-Tree against the prior state-of-the-art. © 2019 IEEE.

Item Type: Conference Paper
Publication: Proceedings of the IEEE International Conference on Computer Vision
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: the copyright of this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords: Computer vision; Modal analysis
Department/Centre: Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited: 01 Apr 2021 11:03
Last Modified: 01 Apr 2021 11:03
URI: http://eprints.iisc.ac.in/id/eprint/65004

Actions (login required)

View Item View Item