Mazumder, A and Baruah, T and Kumar, B and Sharma, R and Pattanaik, V and Rathore, P (2024) Learning Low-Rank Latent Spaces with Simple Deterministic Autoencoder: Theoretical and Empirical Insights. In: UNSPECIFIED, pp. 2839-2848.
|
PDF
WACV_low_ran_lat_spa_sim_det_aut_the_emp_ins_2024.pdf - Published Version Download (2MB) | Preview |
Abstract
The autoencoder is an unsupervised learning paradigm that aims to create a compact latent representation of data by minimizing the reconstruction loss. However, it tends to overlook the fact that most data (images) are embedded in a lower-dimensional latent space, which is crucial for effective data representation. To address this limitation, we propose a novel approach called Low-Rank Autoencoder (LoRAE). In LoRAE, we incorporated a low-rank regularizer to adaptively learn a low-dimensional latent space while preserving the basic objective of an autoencoder. This helps embed the data in a lower-dimensional latent space while preserving important information. It is a simple autoencoder extension that learns low-rank latent space. Theoretically, we establish a tighter error bound for our model. Empirically, our model's superiority shines through various tasks such as image generation and downstream classification. Both theoretical and practical outcomes highlight the importance of acquiring low-dimensional embeddings. © 2024 IEEE.
| Item Type: | Conference Paper |
|---|---|
| Publication: | Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 |
| Publisher: | Institute of Electrical and Electronics Engineers Inc. |
| Additional Information: | The copyright for this article belongs to authors. |
| Department/Centre: | Division of Interdisciplinary Sciences > Center for Infrastructure, Sustainable Transportation and Urban Planning (CiSTUP) Division of Interdisciplinary Sciences > Robert Bosch Centre for Cyber Physical Systems |
| Date Deposited: | 27 May 2024 05:53 |
| Last Modified: | 27 May 2024 05:53 |
| URI: | https://eprints.iisc.ac.in/id/eprint/85037 |
Actions (login required)
 |
View Item |
