Joint Forecasting of Panoptic Segmentations With Difference Attention

Colin Graber, Cyril Jazra, Wenjie Luo, Liangyan Gui, Alexander G. Schwing; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 2627-2636

Abstract


Forecasting of a representation is important for safe and effective autonomy. For this, panoptic segmentations have been studied as a compelling representation in recent work. However, recent state-of-the-art on panoptic segmentation forecasting suffers from two issues: first, individual object instances are treated independently of each other; second, individual object instance forecasts are merged in a heuristic manner. To address both issues, we study a new panoptic segmentation forecasting model that jointly forecasts all object instances in a scene using a transformer model based on 'difference attention.' It further refines the predictions by taking depth estimates into account. We evaluate the proposed model on the Cityscapes and AIODrive datasets. We find difference attention to be particularly suitable for forecasting because the difference of quantities like locations enables a model to explicitly reason about velocities and acceleration. Because of this, we attain state-of-the-art on panoptic segmentation forecasting metrics.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Graber_2022_CVPR, author = {Graber, Colin and Jazra, Cyril and Luo, Wenjie and Gui, Liangyan and Schwing, Alexander G.}, title = {Joint Forecasting of Panoptic Segmentations With Difference Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2627-2636} }