MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2024, 00, pp. 1196-1205
- Issue Date:
- 2024-01-15
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| 1721237.pdf | Published version | 3.3 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Recently semantic segmentation models trained with image level text supervision have shown promising results in challenging open world scenarios However these models still face difficulties in learning fine grained semantic alignment at the pixel level and predicting accurate object masks To address this issue we propose MixReorg a novel and straightforward pre training paradigm for semantic segmentation that enhances a model s ability to reorganize patches mixed across images exploring both local visual relevance and global semantic coherence Our approach involves generating fine grained patch text pairs data by mixing image patches while preserving the correspondence between patches and text The model is then trained to minimize the segmentation loss of the mixed images and the two contrastive losses of the original and restored features With MixReorg as a mask learner conventional text supervised semantic segmentation models can achieve highly generalizable pixel semantic alignment ability which is crucial for open world segmentation After training with large scale image text data MixReorg models can be applied directly to segment visual objects of arbitrary categories without the need for further fine tuning Our proposed framework demonstrates strong performance on popular zero shot semantic segmentation benchmarks outperforming GroupViT by significant margins of 5 0 6 2 2 5 and 3 4 mIoU on PASCAL VOC2012 PASCAL Context MS COCO and ADE20K respectively
Please use this identifier to cite or link to this item: