We lifted 9 functions out of this paper's own repositories and ran 9 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 |
|---|---|---|
| bobby-he/uncertainr | canonical | 9 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| MC_dropout | Ran | bobby-he/uncertainr/modules.py code served (permissive licence) · get_code("a91dafdf4d09eeb2") |
| compute_regularization | Ran | bobby-he/uncertainr/numpyro_port.py code served (permissive licence) · get_code("fac3c05bd2f08140") |
| ct_project | Ran | bobby-he/uncertainr/numpyro_port.py code served (permissive licence) · get_code("27e9cc16949675e8") |
| get_mgrid | Ran | bobby-he/uncertainr/dataio.py code served (permissive licence) · get_code("c3c376e19f06a842") |
| image_mse | Ran | bobby-he/uncertainr/loss_functions.py code served (permissive licence) · get_code("196981f676d3a9d8") |
| image_mse_uncertain | Ran | bobby-he/uncertainr/loss_functions.py code served (permissive licence) · get_code("7b2f5bc9e0c78615") |
| lin2img | Ran | bobby-he/uncertainr/dataio.py code served (permissive licence) · get_code("9d902c538061fea5") |
| normal_nll | Ran | bobby-he/uncertainr/loss_functions.py code served (permissive licence) · get_code("f67fcc6b7a31ebd4") |
| uniform_zero_pad_img | Ran | bobby-he/uncertainr/dataio.py code served (permissive licence) · get_code("1e13df6f5170b938") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Implicit neural representations (INRs) have achieved impressive results for scene reconstruction and computer graphics, where their performance has primarily been assessed on reconstruction accuracy. As INRs make their way into other domains, where model predictions inform high-stakes decision-making, uncertainty quantification of INR inference is becoming critical. To that end, we study a Bayesian reformulation of INRs, UncertaINR, in the context of computed tomography, and evaluate several Bayesian deep learning implementations in terms of accuracy and calibration. We find that they achieve well-calibrated uncertainty, while retaining accuracy competitive with other classical, INR-based, and CNN-based reconstruction techniques. Contrary to common intuition in the Bayesian deep learning literature, we find that INRs obtain the best calibration with computationally efficient Monte Carlo dropout, outperforming Hamiltonian Monte Carlo and deep ensembles. Moreover, in contrast to the best-performing prior approaches, UncertaINR does not require a large training dataset, but only a handful of validation images.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2202.10847")
get_code_for_paper("2202.10847")
have("2202.10847")
Connect an agent — have() is free.