Comparison of Autoencoders for tokenization of ASL datasets
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912185515507712 |
|---|---|
| author | Praun-Petrovic, Vouk Koundinya, Aadhvika Prahallad, Lavanya |
| author_facet | Praun-Petrovic, Vouk Koundinya, Aadhvika Prahallad, Lavanya |
| contents | Generative AI, powered by large language models (LLMs), has revolutionized applications across text, audio, images, and video. This study focuses on developing and evaluating encoder-decoder architectures for the American Sign Language (ASL) image dataset, consisting of 87,000 images across 29 hand sign classes. Three approaches were compared: Feedforward Autoencoders, Convolutional Autoencoders, and Diffusion Autoencoders. The Diffusion Autoencoder outperformed the others, achieving the lowest mean squared error (MSE) and highest Mean Opinion Score (MOS) due to its probabilistic noise modeling and iterative denoising capabilities. The Convolutional Autoencoder demonstrated effective spatial feature extraction but lacked the robustness of the diffusion process, while the Feedforward Autoencoder served as a baseline with limitations in handling complex image data. Objective and subjective evaluations confirmed the superiority of the Diffusion Autoencoder for high-fidelity image reconstruction, emphasizing its potential in multimodal AI applications such as sign language recognition and generation. This work provides critical insights into designing robust encoder-decoder systems to advance multimodal AI capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_06942 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparison of Autoencoders for tokenization of ASL datasets Praun-Petrovic, Vouk Koundinya, Aadhvika Prahallad, Lavanya Machine Learning Computer Vision and Pattern Recognition Generative AI, powered by large language models (LLMs), has revolutionized applications across text, audio, images, and video. This study focuses on developing and evaluating encoder-decoder architectures for the American Sign Language (ASL) image dataset, consisting of 87,000 images across 29 hand sign classes. Three approaches were compared: Feedforward Autoencoders, Convolutional Autoencoders, and Diffusion Autoencoders. The Diffusion Autoencoder outperformed the others, achieving the lowest mean squared error (MSE) and highest Mean Opinion Score (MOS) due to its probabilistic noise modeling and iterative denoising capabilities. The Convolutional Autoencoder demonstrated effective spatial feature extraction but lacked the robustness of the diffusion process, while the Feedforward Autoencoder served as a baseline with limitations in handling complex image data. Objective and subjective evaluations confirmed the superiority of the Diffusion Autoencoder for high-fidelity image reconstruction, emphasizing its potential in multimodal AI applications such as sign language recognition and generation. This work provides critical insights into designing robust encoder-decoder systems to advance multimodal AI capabilities. |
| title | Comparison of Autoencoders for tokenization of ASL datasets |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.06942 |