Jian Wang, Miaomiao Zhang
We lifted 11 functions out of this paper's own repositories and ran 5 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 |
|---|---|---|
| jw4hv/Geo-SIC | canonical | 5 of 11 |
| Function | Status | Where it lives |
|---|---|---|
| det_2x2 | Ran | jw4hv/Geo-SIC/lagomorph/affine.py code served (permissive licence) · get_code("eacd4cfefb3b223f") |
| get_grid2 | Ran | jw4hv/Geo-SIC/networks.py code served (permissive licence) · get_code("78e8ef3944d323bb") |
| invert_2x2 | Ran | jw4hv/Geo-SIC/lagomorph/affine.py code served (permissive licence) · get_code("2661ba54403ce67b") |
| read_yaml | Ran | jw4hv/Geo-SIC/Run_Atlas_trainer.py code served (permissive licence) · get_code("a00707fbd531933c") |
| read_yaml | Ran | jw4hv/Geo-SIC/Run_trainer.py code served (permissive licence) · get_code("b2da2e2efd44e82b") |
| Ad_star | Not yet run | jw4hv/Geo-SIC/lagomorph/adjrep.py code served (permissive licence) · get_code("df92f7ca626018e6") |
| Torchinterp | Not yet run | jw4hv/Geo-SIC/networks.py code served (permissive licence) · get_code("64f6a63a2c4f1b04") |
| ad | Not yet run | jw4hv/Geo-SIC/lagomorph/adjrep.py code served (permissive licence) · get_code("abd776c7576aea25") |
| ad_star | Not yet run | jw4hv/Geo-SIC/lagomorph/adjrep.py code served (permissive licence) · get_code("e2d5c41f9ab0c4e3") |
| minor | Not yet run | jw4hv/Geo-SIC/lagomorph/affine.py code served (permissive licence) · get_code("d2a902ab3b256393") |
| store_config_args | Not yet run | jw4hv/Geo-SIC/modelio.py code served (permissive licence) · get_code("e1a742729c3411e5") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Deformable shapes provide important and complex geometric features of objects presented in images. However, such information is oftentimes missing or underutilized as implicit knowledge in many image analysis tasks. This paper presents Geo-SIC, the first deep learning model to learn deformable shapes in a deformation space for an improved performance of image classification. We introduce a newly designed framework that (i) simultaneously derives features from both image and latent shape spaces with large intra-class variations; and (ii) gains increased model interpretability by allowing direct access to the underlying geometric features of image data. In particular, we develop a boosted classification network, equipped with an unsupervised learning of geometric shape representations characterized by diffeomorphic transformations within each class. In contrast to previous approaches using pre-extracted shapes, our model provides a more fundamental approach by naturally learning the most relevant shape features jointly with an image classifier. We demonstrate the effectiveness of our method on both simulated 2D images and real 3D brain magnetic resonance (MR) images. Experimental results show that our model substantially improves the image classification accuracy with an additional benefit of increased model interpretability. Our code is publicly available at https://github.com/jw4hv/Geo-SIC
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.13704")
get_code_for_paper("2210.13704")
have("2210.13704")
Connect an agent — have() is free.