Research map / Label-efficient and robust learning / Self-supervised and contrastive
MultiSiam: Self-Supervised Multi-Instance Siamese Representation Learning for Autonomous Driving
Kai Chen, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-Yan Yeung
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 |
|---|---|---|---|
| add IoU threshold 0.5 to random cropping (ablation) | BYOL · Cityscapes val mIoU (ablation) | mIoU: 67.2 -> 69.2 | Improved |
| add intra-image clustering loss (ablation) | MultiSiam · Cityscapes val mIoU (ablation) | mIoU: 69.2 -> 70.0 | Improved |
| add self-attention to the predictor (ablation) | MultiSiam · Cityscapes val mIoU (ablation) | mIoU: 70.0 -> 71.2 | Improved |
| add offset alignment (ablation) | MultiSiam · Cityscapes val mIoU (ablation) | mIoU: 71.2 -> 71.9 | Improved |
| add feature alignment (RoI) to 2D feature maps (ablation) | MultiSiam · Cityscapes val mIoU (ablation) | mIoU: 68.8 -> 70.0 | Improved |
| normalize offset coordinates (ablation) | MultiSiam · Cityscapes val mIoU (ablation) | mIoU: 71.2 -> 71.9 | Improved |
| raise IoU threshold from 0.5 to 0.7 (ablation) | MultiSiam · Cityscapes val mIoU (ablation) | mIoU: 70.0 -> 69.2 | Hurt |
| use K=3 clusters instead of K=4 (ablation) | MultiSiam · Cityscapes val mIoU (ablation) | mIoU: 68.4 -> 70.0 | Improved |
| predict cluster centroids instead of dense clustering (ablation) | MultiSiam · Cityscapes val mIoU (ablation) | mIoU: 69.0 -> 70.0 | Improved |
| use K-means cluster targets instead of per-pixel targets (ablation) | MultiSiam · Cityscapes | mIoU: 71.0 -> 74.1 | Improved |
| add residual connection in self-attention with offset alignment (ablation) | MultiSiam · Cityscapes val mIoU (ablation) | mIoU: 71.9 -> 70.0 | Hurt |
| swap pre-training data from ImageNet to Waymo | MoCo-v2 · Cityscapes semantic segmentation | mIoU: 75.7 -> 73.6 | Hurt |
Closest papers by meaning
- One Million Scenes for Autonomous Driving: ONCE Dataset (NeurIPS 2021 · similarity 0.88)
- SelfD: Self-Learning Large-Scale Driving Policies From the Web (CVPR 2022 · similarity 0.88)
- VLM2Scene: Self-Supervised Image-Text-LiDAR Learning with Foundation Models for Autonomous Driving Scene Understanding (AAAI 2024 · similarity 0.87)
- Enhancing End-to-End Autonomous Driving with Latent World Model (ICLR 2025 · similarity 0.87)
- S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Model with Spatio-Temporal Visual Representation (CVPR 2025 · similarity 0.86)
- MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding (CVPR 2024 · similarity 0.86)
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.
