Method Details
Details for method 'Axial-DeepLab-L [Cityscapes-fine]'
Method overview
| name | Axial-DeepLab-L [Cityscapes-fine] |
| challenge | panoptic 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 |
| runtime | n/a |
| subsampling | no |
| submission date | March, 2020 |
| previous submissions |
Average results
| Metric | All | Things | Stuff |
|---|---|---|---|
| PQ | 62.69 | 53.3849 | 69.4572 |
| SQ | 82.2246 | 80.7395 | 83.3047 |
| RQ | 75.3426 | 66.0351 | 82.1118 |
Class results
| Class | PQ | SQ | RQ |
|---|---|---|---|
| road | 98.4463 | 98.5762 | 99.8682 |
| sidewalk | 77.6845 | 84.9788 | 91.4163 |
| building | 88.5715 | 90.8831 | 97.4565 |
| wall | 37.9409 | 76.319 | 49.7136 |
| fence | 40.6441 | 75.4074 | 53.8993 |
| pole | 63.3451 | 70.8862 | 89.3617 |
| traffic light | 59.4405 | 75.3165 | 78.921 |
| traffic sign | 71.6372 | 80.139 | 89.3912 |
| vegetation | 90.7028 | 91.608 | 99.0119 |
| terrain | 45.1792 | 79.0123 | 57.18 |
| sky | 90.4375 | 93.225 | 97.01 |
| person | 53.8033 | 77.568 | 69.3628 |
| rider | 50.8249 | 73.2406 | 69.3944 |
| car | 66.7299 | 85.2538 | 78.2721 |
| truck | 47.5902 | 87.3097 | 54.5073 |
| bus | 61.1182 | 89.0364 | 68.6441 |
| train | 57.6522 | 83.8577 | 68.75 |
| motorcycle | 46.9832 | 77.0873 | 60.9481 |
| bicycle | 42.3776 | 72.5623 | 58.4017 |