Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Chenxi Liu, Liang-Chieh Chen, Florian Schroff, Hartwig Adam, Wei Hua, Alan Yuille, Li Fei-Fei
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/tensorflow/modelsOfficialIn papertf★ 77,694
- github.com/NoamRosenberg/autodeeplabpytorch★ 0
- github.com/2024-MindSpore-1/Code6/tree/main/Auto-DeepLabmindspore★ 0
- github.com/MenghaoGuo/AutoDeeplabpytorch★ 0
- github.com/mindspore-ai/models/tree/master/research/cv/Auto-DeepLabmindspore★ 0
- github.com/MindSpore-paper-code-3/code6/tree/main/Auto-DeepLabmindspore★ 0
- github.com/Mind23-2/MindCode-7mindspore★ 0
- github.com/2023-MindSpore-4/Code8/tree/main/Auto-DeepLabmindspore★ 0
- github.com/2023-MindSpore-1/ms-code-16/tree/main/Auto-DeepLabmindspore★ 0
- github.com/Dawars/auto_deeplab-pytorchpytorch★ 0
Abstract
Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for semantic image segmentation, attains state-of-the-art performance without any ImageNet pretraining.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| ADE20K | Auto-DeepLab-L | Validation mIoU | 43.98 | — | Unverified |
| ADE20K val | Auto-DeepLab-L | mIoU | 43.98 | — | Unverified |
| Cityscapes test | Auto-DeepLab-L | Mean IoU (class) | 82.1 | — | Unverified |
| Cityscapes val | Auto-DeepLab-L | mIoU | 80.33 | — | Unverified |
| PASCAL VOC 2012 test | Auto-DeepLab-L | Mean IoU | 85.6 | — | Unverified |
| PASCAL VOC 2012 val | Auto-DeepLab-L | mIoU | 82.04 | — | Unverified |