We lifted 3 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| facebookresearch/capi | canonical | 2 of 2 |
| copy not recorded | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| accuracy | Ran | facebookresearch/capi/eval_segmentation.py code served (permissive licence) · get_code("9f4da55ba3d8c0ea") |
| mIoU | Ran | facebookresearch/capi/eval_segmentation.py code served (permissive licence) · get_code("22561ceffe38fff8") |
| rotate_half | Ran | this paper's copy was not recorded; identical code first harvested from tdooms/bilinear-decomposition pointer only · get_code("437c7011506995a3") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Masked Image Modeling (MIM) offers a promising approach to self-supervised representation learning, however existing MIM models still lag behind the state-of-the-art. In this paper, we systematically analyze target representations, loss functions, and architectures, to introduce CAPI - a novel pure-MIM framework that relies on the prediction of latent clusterings. Our approach leverages a clustering-based loss, which is stable to train, and exhibits promising scaling properties. Our ViT-L backbone, CAPI, achieves 83.8% accuracy on ImageNet and 32.1% mIoU on ADE20K with simple linear probes, substantially outperforming previous MIM methods and approaching the performance of the current state-of-the-art, DINOv2. We release all our code and models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2502.08769")
get_code_for_paper("2502.08769")
have("2502.08769")
Connect an agent — have() is free.