TBH-VAE
Code for deep image hashing based on twin-bottleneck architecture with variational autoencoders.
Description:
Repository for reproducing results of our paper “Deep image hashing based on twin-bottleneck hashing with variational autoencoders” (Verwilst 2021). It contains the code for training the twin-bottleneck variational autoencoder architecture, evaluating the learned hash function, and performing content-based image retrieval using the learned hash function.
More Information:
- Grand Challenge/Workpackage(s): GC1 - WP4
- Responsible Research Lead: Aleksandra Pizurica
- Authors: Maxim Verwilst, Nina Zizakic, Lingchen Gu
- Programming Language: Python
- Link to the repository
- Categories: Un/Semi-supervised learning, Images
Publications:
- M. Verwilst, N. Zizakic, L. Gu, A. Pizurica, “Deep image hashing based on twin-bottleneck hashing with variational autoencoders”, IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), 2021.
