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 |
|---|---|---|
| HAHA-DL/MLDG | pwc_unofficial | 3 of 6 |
| Pulkit-Khandelwal/mldg | pwc_unofficial | 2 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| default_flist_reader | Ran | Pulkit-Khandelwal/mldg/data_reader.py code served (permissive licence) · get_code("a2d01766b58dccb1") |
| default_loader | Ran | Pulkit-Khandelwal/mldg/data_reader.py code served (permissive licence) · get_code("ac269a0e4b8d946e") |
| shuffle_data | Ran | HAHA-DL/MLDG/utils.py code served (permissive licence) · get_code("e66d8098b50090e3") |
| shuffle_list | Ran | HAHA-DL/MLDG/utils.py code served (permissive licence) · get_code("c63cc42fd5b3834f") |
| unfold_label | Ran | HAHA-DL/MLDG/utils.py code served (permissive licence) · get_code("704f4addaa30438d") |
| conv2d | Not yet run | HAHA-DL/MLDG/ops.py code served (permissive licence) · get_code("0e943019e82fc2c6") |
| conv2d | Not yet run | Pulkit-Khandelwal/mldg/ops.py code served (permissive licence) · get_code("de1ae463b706fe80") |
| linear | Not yet run | HAHA-DL/MLDG/ops.py code served (permissive licence) · get_code("784b369d16cde8f9") |
| relu | Not yet run | HAHA-DL/MLDG/ops.py code served (permissive licence) · get_code("982640b2b87ab733") |
| relu | Not yet run | Pulkit-Khandelwal/mldg/ops.py code served (permissive licence) · get_code("ffc6304fe71748bf") |
| yo | Not yet run | Pulkit-Khandelwal/mldg/mlp2.py code served (permissive licence) · get_code("825eed11509a6aa2") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. {Domain Generalization} (DG) techniques attempt to alleviate this issue by producing models which by design generalize well to novel testing domains. We propose a novel {meta-learning} method for domain generalization. Rather than designing a specific model that is robust to domain shift as in most previous DG work, we propose a model agnostic training procedure for DG. Our algorithm simulates train/test domain shift during training by synthesizing virtual testing domains within each mini-batch. The meta-optimization objective requires that steps to improve training domain performance should also improve testing domain performance. This meta-learning procedure trains models with good generalization ability to novel domains. We evaluate our method and achieve state of the art results on a recent cross-domain image classification benchmark, as well demonstrating its potential on two classic reinforcement learning tasks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1710.03463")
get_code_for_paper("1710.03463")
have("1710.03463")
Connect an agent — have() is free.