Open-Vocabulary Panoptic Segmentation Using BERT Pre-Training of Vision-Language Multiway Transformer Model
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_ | 1866929648546349056 |
|---|---|
| author | Chen, Yi-Chia Li, Wei-Hua Chen, Chu-Song |
| author_facet | Chen, Yi-Chia Li, Wei-Hua Chen, Chu-Song |
| contents | Open-vocabulary panoptic segmentation remains a challenging problem. One of the biggest difficulties lies in training models to generalize to an unlimited number of classes using limited categorized training data. Recent popular methods involve large-scale vision-language pre-trained foundation models, such as CLIP. In this paper, we propose OMTSeg for open-vocabulary segmentation using another large-scale vision-language pre-trained model called BEiT-3 and leveraging the cross-modal attention between visual and linguistic features in BEiT-3 to achieve better performance. Experiments result demonstrates that OMTSeg performs favorably against state-of-the-art models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18917 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Open-Vocabulary Panoptic Segmentation Using BERT Pre-Training of Vision-Language Multiway Transformer Model Chen, Yi-Chia Li, Wei-Hua Chen, Chu-Song Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Open-vocabulary panoptic segmentation remains a challenging problem. One of the biggest difficulties lies in training models to generalize to an unlimited number of classes using limited categorized training data. Recent popular methods involve large-scale vision-language pre-trained foundation models, such as CLIP. In this paper, we propose OMTSeg for open-vocabulary segmentation using another large-scale vision-language pre-trained model called BEiT-3 and leveraging the cross-modal attention between visual and linguistic features in BEiT-3 to achieve better performance. Experiments result demonstrates that OMTSeg performs favorably against state-of-the-art models. |
| title | Open-Vocabulary Panoptic Segmentation Using BERT Pre-Training of Vision-Language Multiway Transformer Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.18917 |