Research map / Detection and segmentation / CNN features
Event Camera Data Dense Pre-training
Yan Yang, Liyuan Pan, Liu liu
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 context-level similarity loss to pre-training (ablation) | Event dense pre-training, Swin-T/7 on E-TartanAir · DSEC semantic segmentation | mIoU / mACC (%): 55.556/63.486 -> 61.250/69.620 | Improved |
| add context-level loss to ECDP objective (ablation) | ECDP (ViT-S/16) · DSEC semantic segmentation | mIoU / mACC (%): 52.517/60.553 -> 53.826/61.008 | Improved |
| pre-train on synthetic E-TartanAir instead of N-ImageNet (ablation) | Event dense pre-training (all backbones) · DSEC semantic segmentation | mIoU (%): 56.654 -> 61.250 (Swin-T/7) | Improved |
| increase number of contexts beyond 8 (ablation) | Context-level similarity loss · DSEC semantic segmentation | mIoU / mACC | Hurt |
| increase pre-training epochs beyond 300 (ablation) | Event dense pre-training · DSEC semantic segmentation | mIoU / mACC | No clear effect |
| use Swin-T/7 backbone instead of ViT-S/16 | Event dense pre-training · DSEC semantic segmentation | mIoU (%): 55.729 -> 61.250 | Improved |
| event-only self-supervised pre-training vs supervised depth pre-training | Ours vs HMNet · MVSEC depth (no cutoff) | RMS: 7.534 -> 6.805 | Improved |
| pre-train with proposed method vs IDNet previous best | Ours (Swin-T/7) · DSEC-Flow | EPE: 0.719 -> 0.697 | Improved |
Closest papers by meaning
- Event Camera Data Pre-training (ICCV 2023 · similarity 0.91)
- Efficient Event Camera Data Pretraining with Adaptive Prompt Fusion (ICCV 2025 · similarity 0.89)
- Video to Events: Recycling Video Datasets for Event Cameras (CVPR 2020 · similarity 0.89)
- Efficient Learning of Event-based Dense Representation using Hierarchical Memories with Adaptive Update (ECCV 2024 · similarity 0.88)
- Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy (CVPR 2021 · similarity 0.88)
- Events-To-Video: Bringing Modern Computer Vision to Event Cameras (CVPR 2019 · similarity 0.88)
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.
