| tags: | |
| - pytorch | |
| - lidar | |
| - 3d-object-detection | |
| - test-time-adaptation | |
| pipeline_tag: object-detection | |
| # FIND Checkpoints | |
| Source-pretrained SECOND-IoU checkpoints for **FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection** (NeurIPS 2026). | |
| Paper: [arXiv:2611.09170](https://arxiv.org/abs/2611.09170) | |
| | Checkpoint | Source dataset | Adaptation task | | |
| | --- | --- | --- | | |
| | [n2k.pth](checkpoints/n2k.pth) | nuScenes | nuScenes → KITTI | | |
| | [w2k.pth](checkpoints/w2k.pth) | Waymo | Waymo → KITTI | | |
| | [k2c.pth](checkpoints/k2c.pth) | KITTI | KITTI → KITTI-C | | |
| Place the downloaded checkpoints in the `checkpoints/` directory of the [FIND codebase](https://github.com/llldx03/FIND). | |
| Follow the [GitHub README](https://github.com/llldx03/FIND#readme) for installation, data preparation, source spectral statistics, and online adaptation. |