Research map / Label-efficient and robust learning / Self-supervised and contrastive
Self-Distilled Feature Aggregation for Self-Supervised Monocular Depth Estimation
Zhengming Zhou, Qiulei Dong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use modified Swin-transformer with high-resolution features (ablation) | Swin+Raw · KITTI raw Eigen | Abs Rel: 0.102 -> 0.100 | Improved |
| replace first decoder block with SDFA (ablation) | Swin-dagger+Raw · KITTI raw Eigen | Abs Rel: 0.100 -> 0.097 | Improved |
| replace three decoder blocks with SDFA (ablation) | Swin-dagger+Raw · KITTI raw Eigen | Abs Rel: 0.100 -> 0.094 | Improved |
| use SDFA with self-distilled offsets instead of offset-based aggregation (ablation) | Swin-dagger+OA · KITTI raw Eigen | RMSE: 4.082 -> 3.896 | Improved |
| use offset-based aggregation instead of concatenation (ablation) | Swin-dagger+Raw · KITTI raw Eigen | Abs Rel: 0.100 -> 0.091 | Mixed |
| train OA with straightforward self-distillation (ablation) | Swin-dagger+OA · KITTI raw Eigen | Abs Rel: 0.091 -> 0.092 | No clear effect |
| add photometric principle mask (ablation) | SDFA-Net · KITTI raw Eigen | Abs Rel: 0.096 -> 0.090 | Improved |
| add visible principle mask (ablation) | SDFA-Net · KITTI raw Eigen | Abs Rel: 0.090 -> 0.090 | No clear effect |
| add both principle masks (ablation) | SDFA-Net · KITTI raw Eigen | Abs Rel: 0.095 -> 0.090 | Improved |
| add feature flipping in self-distilled propagation (ablation) | SDFA-Net · KITTI raw Eigen | Abs Rel: 0.097 -> 0.090 | Improved |
| use SDFA with ResNet18 encoder instead of concatenation (ablation) | Res18+Raw · KITTI raw Eigen | Abs Rel: 0.102 -> 0.101 | Improved |
| add Cityscapes to KITTI training | SDFA-Net (PP) · KITTI raw Eigen | Abs Rel: 0.089 -> 0.084 | Improved |
Closest papers by meaning
- Exploiting Pseudo Labels in a Self-Supervised Learning Framework for Improved Monocular Depth Estimation (CVPR 2022 · similarity 0.90)
- Digging Into Self-Supervised Monocular Depth Estimation (ICCV 2019 · similarity 0.89)
- Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation (ICCV 2021 · similarity 0.89)
- Self-Supervised Monocular Trained Depth Estimation Using Self-Attention and Discrete Disparity Volume (CVPR 2020 · similarity 0.89)
- Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation (ICCV 2021 · similarity 0.89)
- BRNet: Exploring Comprehensive Features for Monocular Depth Estimation (ECCV 2022 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
