SwiFT (4D Swin fMRI Transformer, Mamba-free predecessor of NeuroSTORM) -- SwiFT HCP-YA sex-classification fine-tune backbone
Description
SwiFT (Kim, Kwon, Moon, Cha et al., arXiv:2307.05916) is a 4D
Swin Transformer for fMRI BOLD volumes. The architecture is the
Mamba-free predecessor of NeuroSTORM -- same 4-stage Swin
topology (depths [2, 2, 6, 2], channels [36, 72, 144, 288],
4D window [4, 4, 4, 4]) but using conventional WindowAttention4D
multi-head self-attention as the per-window mixer instead of
NeuroSTORM's Mamba selective-scan SSM.
v0 ships two variants:
contrastive -- the contrastive-pretraining checkpoint
(SimCLR-style backbone trained on a multi-cohort fMRI corpus).
Use as a frozen feature extractor for downstream tasks.hcp-sex -- the supervised fine-tune on HCP-YA sex
classification. Same architecture as contrastive; weights
have been further fine-tuned end-to-end. Use as a starting
point for additional fine-tuning or as an HCP-specific feature
extractor.
The bundle stores only the backbone (SwinTransformer4D) --
the consumer-side SimCLR projection (emb_mlp) and the
downstream task heads (clf.head, reg.head) are training-
time plumbing and are dropped at extract.
Intended use
HCP-YA sex-classification fine-tuned variant. Same backbone topology as the contrastive variant; the weights have been further fine-tuned on the supervised classification task. Use as an HCP-specific feature extractor OR as initialisation for additional fine-tuning. The classifier head (clf.head) is NOT in the bundle -- add your own downstream MLP on the (288, 2, 2, 2, 20) backbone embedding.
Usage
1from ilex.models.swift import SwiFT
2model = SwiFT.from_pretrained('ilex-hub/swift.hcp-sex.1')
Authors
Kim P. Y., Kwon J., Moon T., Cha J. (Seoul National University M.IN.D Lab + Connectome Lab)
Citation
Kim P. Y., Kwon J., Moon T., Cha J. et al. (2023). SwiFT -- Swin 4D fMRI Transformer. arXiv 2307.05916.
References
- Kim P. Y., Kwon J., Moon T., Cha J. et al. (2023). SwiFT -- Swin 4D fMRI Transformer. arXiv:2307.05916.
- Liu Z. et al. (2021). Swin Transformer -- Hierarchical Vision Transformer using Shifted Windows. arXiv:2103.14030.
- Upstream code + weights -- github.com/Transconnectome/SwiFT (Apache-2.0).
License
HF Hub license tag: apache-2.0
Effective terms: Apache-2.0 (both upstream code and the in-tree pretrained .ckpt checkpoints at github.com/Transconnectome/SwiFT). The ilex JAX / Equinox port code is separately Apache-2.0 / GPL-3.0.
Copyright
SwiFT is copyright (c) Transconnectome / Seoul National
University 2023, Apache-2.0-licensed on the upstream code +
the in-tree pretrained checkpoints
(github.com/Transconnectome/SwiFT). The ilex JAX / Equinox port
code is separately licensed under Apache-2.0 / GPL-3.0.
Upstream source
Original weights / reference implementation:
https://github.com/Transconnectome/SwiFTProvenance
This artefact was produced by
ilex's
save/load pipeline. The architecture is implemented in
ilex.models.swift.SwiFT and the weights have been converted
from their upstream format. See the upstream source above
for the canonical reference.
