Token Turing Machines are Efficient Vision Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916580921704448 |
|---|---|
| author | Jajal, Purvish Eliopoulos, Nick John Chou, Benjamin Shiue-Hal Thiruvathukal, George K. Davis, James C. Lu, Yung-Hsiang |
| author_facet | Jajal, Purvish Eliopoulos, Nick John Chou, Benjamin Shiue-Hal Thiruvathukal, George K. Davis, James C. Lu, Yung-Hsiang |
| contents | We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual understanding tasks. ViTTMs are designed for non-sequential computer vision tasks such as image classification and segmentation. Our model creates two sets of tokens: process tokens and memory tokens; process tokens pass through encoder blocks and read-write from memory tokens at each encoder block in the network, allowing them to store and retrieve information from memory. By ensuring that there are fewer process tokens than memory tokens, we are able to reduce the inference time of the network while maintaining its accuracy. On ImageNet-1K, the state-of-the-art ViT-B has median latency of 529.5ms and 81.0% accuracy, while our ViTTM-B is 56% faster (234.1ms), with 2.4 times fewer FLOPs, with an accuracy of 82.9%. On ADE20K semantic segmentation, ViT-B achieves 45.65mIoU at 13.8 frame-per-second (FPS) whereas our ViTTM-B model acheives a 45.17 mIoU with 26.8 FPS (+94%). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07613 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Token Turing Machines are Efficient Vision Models Jajal, Purvish Eliopoulos, Nick John Chou, Benjamin Shiue-Hal Thiruvathukal, George K. Davis, James C. Lu, Yung-Hsiang Computer Vision and Pattern Recognition Machine Learning We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual understanding tasks. ViTTMs are designed for non-sequential computer vision tasks such as image classification and segmentation. Our model creates two sets of tokens: process tokens and memory tokens; process tokens pass through encoder blocks and read-write from memory tokens at each encoder block in the network, allowing them to store and retrieve information from memory. By ensuring that there are fewer process tokens than memory tokens, we are able to reduce the inference time of the network while maintaining its accuracy. On ImageNet-1K, the state-of-the-art ViT-B has median latency of 529.5ms and 81.0% accuracy, while our ViTTM-B is 56% faster (234.1ms), with 2.4 times fewer FLOPs, with an accuracy of 82.9%. On ADE20K semantic segmentation, ViT-B achieves 45.65mIoU at 13.8 frame-per-second (FPS) whereas our ViTTM-B model acheives a 45.17 mIoU with 26.8 FPS (+94%). |
| title | Token Turing Machines are Efficient Vision Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2409.07613 |