REGION-DINO β€” teacher checkpoints (RATS)

Self-supervised REGION-DINO backbones whose register tokens latch onto coherent image regions, enabling RATS (recursive register decomposition + grouping) for label-free, part-to-whole segmentation.

πŸ”¬ Demo: https://huggingface.co/spaces/TimingYang/RATS

These are teacher-only weights, saved every 20 epochs plus the final epoch.

Models

variant arch embed register tokens regs/head epochs per-ckpt
base region_vit_base 768 192 16 400 (final 388) ~436 MB
small region_vit_small 384 96 16 300 ~176 MB

Both use patch size 16, cross-attention, num_reg_for_loss_per_head=16.

Files

base/   checkpoint_teacher_ep0020.pth … ep0380.pth, ep0388.pth   (20 ckpts)
small/  checkpoint_teacher_ep0020.pth … ep0300.pth               (15 ckpts)

Each file is a dict {"teacher": state_dict} (the EMA teacher backbone + head).

Usage

import torch
from huggingface_hub import hf_hub_download
import vision_transformer as vits  # from the RATS repo / Space

ckpt = hf_hub_download("TimingYang/RATS", "base/checkpoint_teacher_ep0388.pth")
state = torch.load(ckpt, map_location="cpu")["teacher"]
state = {k.replace("module.", "").replace("backbone.", ""): v for k, v in state.items()}

model = vits.region_vit_base(patch_size=16, num_register_tokens=192,
                             use_cross_attn=True, num_reg_for_loss_per_head=16)
model.load_state_dict(state, strict=False)   # head.* keys are unused for features
model.eval()

For small, use vits.region_vit_small(num_register_tokens=96, ...).

License

Apache-2.0. Built on facebookresearch/dino.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support