We lifted 14 functions out of this paper's own repositories and ran 11 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 |
|---|---|---|
| YSale/label-uq | canonical | 11 of 14 |
| Function | Status | Where it lives |
|---|---|---|
| accuracy | Ran | YSale/label-uq/arc_ood/utils.py pointer only (licence: GPL-3.0) · get_code("ef6da3c8f8497e94") |
| aleatoric_uncertainty_variance | Ran | YSale/label-uq/holdout/unc_label.py pointer only (licence: GPL-3.0) · get_code("f3921a2f331761fa") |
| aleatoric_uncertainty_variance | Ran | YSale/label-uq/arc_ood/uncertainty.py pointer only (licence: GPL-3.0) · get_code("4d542a15c47ad321") |
| append_array | Ran | YSale/label-uq/arc_ood/utils.py pointer only (licence: GPL-3.0) · get_code("1481be59d3acc642") |
| epistemic_uncertainty_variance | Ran | YSale/label-uq/holdout/unc_label.py pointer only (licence: GPL-3.0) · get_code("f96930278eed1ed5") |
| epistemic_uncertainty_variance | Ran | YSale/label-uq/arc_ood/uncertainty.py pointer only (licence: GPL-3.0) · get_code("49995991be7d33fc") |
| get_data | Ran | YSale/label-uq/arc_ood/data.py pointer only (licence: GPL-3.0) · get_code("ebe31a9076be0d2b") |
| get_data | Ran | YSale/label-uq/holdout/data.py pointer only (licence: GPL-3.0) · get_code("baf5a792dc1a4a95") |
| get_probs | Ran | YSale/label-uq/holdout/data.py pointer only (licence: GPL-3.0) · get_code("259d23a3b6e83ce7") |
| total_uncertainty_variance | Ran | YSale/label-uq/holdout/unc_label.py pointer only (licence: GPL-3.0) · get_code("cf3dab7fb4f63630") |
| total_uncertainty_variance | Ran | YSale/label-uq/arc_ood/uncertainty.py pointer only (licence: GPL-3.0) · get_code("9b5cd0c059dd3261") |
| get_resnet50 | Not yet run | YSale/label-uq/medical/models.py pointer only (licence: GPL-3.0) · get_code("4fd78ff184dad0c4") |
| torch_get_outputs | Not yet run | YSale/label-uq/arc_ood/utils.py pointer only (licence: GPL-3.0) · get_code("325291a8a89d7777") |
| train_ensemble | Not yet run | YSale/label-uq/holdout/holdout.py pointer only (licence: GPL-3.0) · get_code("2b9efd66fa8cd036") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of uncertainty measures. This label-wise perspective allows uncertainty to be quantified at the individual class level, thereby improving cost-sensitive decision-making and helping understand the sources of uncertainty. Furthermore, it allows to define total, aleatoric, and epistemic uncertainty on the basis of non-categorical measures such as variance, going beyond common entropy-based measures. In particular, variance-based measures address some of the limitations associated with established methods that have recently been discussed in the literature. We show that our proposed measures adhere to a number of desirable properties. Through empirical evaluation on a variety of benchmark data sets -- including applications in the medical domain where accurate uncertainty quantification is crucial -- we establish the effectiveness of label-wise uncertainty quantification.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.02354")
get_code_for_paper("2406.02354")
have("2406.02354")
Connect an agent — have() is free.