Generalizable Implicit Neural Representations via Instance Pattern Composers
- Title
- Generalizable Implicit Neural Representations via Instance Pattern Composers
- Authors
- Kim, Chiheon; Lee, Doyup; Kim, Saehoon; Cho, Minsu; Han, Wook-Shin
- Date Issued
- 2023-06
- Publisher
- IEEE Computer Society
- Abstract
- Despite recent advances in implicit neural representations (INRs), it remains challenging for a coordinate-based multi-layer perceptron (MLP) of INRs to learn a common representation across data instances and generalize it for unseen instances. In this work, we introduce a simple yet effective framework for generalizable INRs that enables a coordinate-based MLP to represent complex data instances by modulating only a small set of weights in an early MLP layer as an instance pattern composer; the remaining MLP weights learn pattern composition rules for common representations across instances. Our generalizable INR frame-work is fully compatible with existing meta-learning and hypernetworks in learning to predict the modulated weight for unseen instances. Extensive experiments demonstrate that our method achieves high performance on a wide range of domains such as an audio, image, and 3D object, while the ablation study validates our weight modulation.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/121038
- Article Type
- Conference
- Citation
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, page. 11808 - 11817, 2023-06
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.