llama2thedog's picture
Fix Recall value (micro vs macro)
6df5e2f verified
|
Raw
History Blame Contribute Delete
2.51 kB
metadata
license: mit
library_name: pytorch
tags:
  - point-cloud
  - 3d
  - classification
  - bim
  - aec
  - ifc
  - building-information-modeling
datasets:
  - ifcnetcore

BIM-JEPA (Finetuned on IFCNetCore)

Classification model finetuned from llama2thedog/BIM-JEPA-pretrained on the IFCNetCore dataset.

Performance (test set)

Metric Value
Overall Accuracy 89.37%
Mean Class Accuracy (macro recall) 86.63%
Precision (macro) 89.38%
Recall (micro) 89.37%
F1 Score (macro) 87.69%

Paper

Self-supervised learning for BIM element classification using a joint embedding predictive architecture
Jack Wei Lun Shi, Wawan Solihin, Yufeng Weng, Yimin Zhao, Leong Hien Poh, Justin K.W. Yeoh
Automation in Construction

Architecture

  • Backbone: BIM-JEPA encoder (12-layer Transformer, 384 dim, 6 heads) — initialized from the pretrained checkpoint
  • Head: MLP classifier, 256 hidden dim, mean+max pooling, 0.5 dropout
  • Loss: Cross-entropy with label smoothing (0.1)
  • Encoder schedule: Frozen for the first 175 epochs, then unfrozen and finetuned end-to-end

Training

Dataset IFCNetCore
Input 4096 points per object
Augmentations Scale, rotate (all axes), translate
Epochs 350
Batch size 32
Optimizer AdamW (head lr=1e-3, encoder lr=1e-4, weight decay 0.05)
Schedule Linear warmup (10 epochs) + cosine decay
Precision bf16-mixed

Full training hyperparameters are in hparams.yaml.

Files

File Size Description
bim_jepa_finetuned_ifcnetcore.ckpt 256 MB PyTorch Lightning checkpoint
hparams.yaml 2 KB Training hyperparameters

Usage

Clone the GitHub repo first to get the model code, then:

from huggingface_hub import hf_hub_download
from bimjepa.models.classification import BimJepaClassification

ckpt_path = hf_hub_download(
    repo_id="llama2thedog/BIM-JEPA-finetuned-ifcnetcore",
    filename="bim_jepa_finetuned_ifcnetcore.ckpt",
)
model = BimJepaClassification.load_from_checkpoint(ckpt_path)
model.eval()

Citation

in progress

License

MIT