TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916495060107264 |
|---|---|
| author | Olszewski, Jan Rymarczyk, Dawid Wójcik, Piotr Pach, Mateusz Zieliński, Bartosz |
| author_facet | Olszewski, Jan Rymarczyk, Dawid Wójcik, Piotr Pach, Mateusz Zieliński, Bartosz |
| contents | Active Visual Exploration (AVE) optimizes the utilization of robotic resources in real-world scenarios by sequentially selecting the most informative observations. However, modern methods require a high computational budget due to processing the same observations multiple times through the autoencoder transformers.
As a remedy, we introduce a novel approach to AVE called TOken REcycling (TORE). It divides the encoder into extractor and aggregator components. The extractor processes each observation separately, enabling the reuse of tokens passed to the aggregator. Moreover, to further reduce the computations, we decrease the decoder to only one block.
Through extensive experiments, we demonstrate that TORE outperforms state-of-the-art methods while reducing computational overhead by up to 90\%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_15335 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration Olszewski, Jan Rymarczyk, Dawid Wójcik, Piotr Pach, Mateusz Zieliński, Bartosz Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Active Visual Exploration (AVE) optimizes the utilization of robotic resources in real-world scenarios by sequentially selecting the most informative observations. However, modern methods require a high computational budget due to processing the same observations multiple times through the autoencoder transformers. As a remedy, we introduce a novel approach to AVE called TOken REcycling (TORE). It divides the encoder into extractor and aggregator components. The extractor processes each observation separately, enabling the reuse of tokens passed to the aggregator. Moreover, to further reduce the computations, we decrease the decoder to only one block. Through extensive experiments, we demonstrate that TORE outperforms state-of-the-art methods while reducing computational overhead by up to 90\%. |
| title | TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.15335 |