Method Details
Details for method 'Axial-DeepLab-XL [Mapillary Vistas]'
Method overview
| name | Axial-DeepLab-XL [Mapillary Vistas] |
| challenge | instance-level semantic labeling |
| details | Convolution exploits locality for efficiency at a cost of missing long range context. Self-attention has been adopted to augment CNNs with non-local interactions. Recent works prove it possible to stack self-attention layers to obtain a fully attentional network by restricting the attention to a local region. In this paper, we attempt to remove this constraint by factorizing 2D self-attention into two 1D self-attentions. This reduces computation complexity and allows performing attention within a larger or even global region. In companion, we also propose a position-sensitive self-attention design. Combining both yields our position-sensitive axial-attention layer, a novel building block that one could stack to form axial-attention models for image classification and dense prediction. We demonstrate the effectiveness of our model on four large-scale datasets. In particular, our model outperforms all existing stand-alone self-attention models on ImageNet. Our Axial-DeepLab improves 2.8% PQ over bottom-up state-of-the-art on COCO test-dev. This previous state-of-the-art is attained by our small variant that is 3.8x parameter-efficient and 27x computation-efficient. Axial-DeepLab also achieves state-of-the-art results on Mapillary Vistas and Cityscapes. |
| publication | Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation Huiyu Wang, Yukun Zhu, Bradley Green, Hartwig Adam, Alan Yuille, Liang-Chieh Chen ECCV 2020 (spotlight) https://arxiv.org/abs/2003.07853 |
| project page / code | https://github.com/csrhddlam/axial-deeplab |
| used Cityscapes data | fine annotations |
| used external data | ImageNet, Mapillary Vistas |
| runtime | n/a |
| subsampling | no |
| submission date | April, 2020 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| AP | 39.6336 |
| AP50% | 64.168 |
| AP100m | 55.479 |
| AP50m | 57.4197 |
Class results
| Class | AP | AP50% | AP100m | AP50m |
|---|---|---|---|---|
| person | 36.5754 | 66.1173 | 56.2342 | 56.3886 |
| rider | 32.4889 | 65.5408 | 47.8991 | 48.3985 |
| car | 56.5951 | 78.9779 | 77.8155 | 80.1814 |
| truck | 40.9977 | 52.9021 | 55.8824 | 62.1738 |
| bus | 52.4269 | 67.7541 | 73.5189 | 78.2301 |
| train | 43.6786 | 65.9702 | 57.2532 | 58.0859 |
| motorcycle | 30.8181 | 62.4789 | 39.6706 | 40.4505 |
| bicycle | 23.4883 | 53.6024 | 35.558 | 35.4492 |