Static-Dynamic Class-level Perception Consistency in Video Semantic Segmentation
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_ | 1866910739422248960 |
|---|---|
| author | Cen, Zhigang Guo, Ningyan Xu, Wenjing Feng, Zhiyong Huang, Danlan |
| author_facet | Cen, Zhigang Guo, Ningyan Xu, Wenjing Feng, Zhiyong Huang, Danlan |
| contents | Video semantic segmentation(VSS) has been widely employed in lots of fields, such as simultaneous localization and mapping, autonomous driving and surveillance. Its core challenge is how to leverage temporal information to achieve better segmentation. Previous efforts have primarily focused on pixel-level static-dynamic contexts matching, utilizing techniques such as optical flow and attention mechanisms. Instead, this paper rethinks static-dynamic contexts at the class level and proposes a novel static-dynamic class-level perceptual consistency (SD-CPC) framework. In this framework, we propose multivariate class prototype with contrastive learning and a static-dynamic semantic alignment module. The former provides class-level constraints for the model, obtaining personalized inter-class features and diversified intra-class features. The latter first establishes intra-frame spatial multi-scale and multi-level correlations to achieve static semantic alignment. Then, based on cross-frame static perceptual differences, it performs two-stage cross-frame selective aggregation to achieve dynamic semantic alignment. Meanwhile, we propose a window-based attention map calculation method that leverages the sparsity of attention points during cross-frame aggregation to reduce computation cost. Extensive experiments on VSPW and Cityscapes datasets show that the proposed approach outperforms state-of-the-art methods. Our implementation will be open-sourced on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08034 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Static-Dynamic Class-level Perception Consistency in Video Semantic Segmentation Cen, Zhigang Guo, Ningyan Xu, Wenjing Feng, Zhiyong Huang, Danlan Computer Vision and Pattern Recognition Video semantic segmentation(VSS) has been widely employed in lots of fields, such as simultaneous localization and mapping, autonomous driving and surveillance. Its core challenge is how to leverage temporal information to achieve better segmentation. Previous efforts have primarily focused on pixel-level static-dynamic contexts matching, utilizing techniques such as optical flow and attention mechanisms. Instead, this paper rethinks static-dynamic contexts at the class level and proposes a novel static-dynamic class-level perceptual consistency (SD-CPC) framework. In this framework, we propose multivariate class prototype with contrastive learning and a static-dynamic semantic alignment module. The former provides class-level constraints for the model, obtaining personalized inter-class features and diversified intra-class features. The latter first establishes intra-frame spatial multi-scale and multi-level correlations to achieve static semantic alignment. Then, based on cross-frame static perceptual differences, it performs two-stage cross-frame selective aggregation to achieve dynamic semantic alignment. Meanwhile, we propose a window-based attention map calculation method that leverages the sparsity of attention points during cross-frame aggregation to reduce computation cost. Extensive experiments on VSPW and Cityscapes datasets show that the proposed approach outperforms state-of-the-art methods. Our implementation will be open-sourced on GitHub. |
| title | Static-Dynamic Class-level Perception Consistency in Video Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.08034 |