We lifted 7 functions out of this paper's own repositories and ran 6 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 |
|---|---|---|
| xch-liu/geom-tex-dg | canonical | 4 of 5 |
| hlzhang109/ddg | reimplementation | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| compute_distance_matrix | Ran | xch-liu/geom-tex-dg/Dassl/dassl/metrics/distance.py code served (permissive licence) · get_code("cbff6e3d6b3109ac") |
| conv3x3 | Ran | xch-liu/geom-tex-dg/Dassl/dassl/modeling/backbone/resnet.py code served (permissive licence) · get_code("fac5364e2f53c6db") |
| cosine_distance | Ran | xch-liu/geom-tex-dg/Dassl/dassl/metrics/distance.py code served (permissive licence) · get_code("e8878931ade705ee") |
| euclidean_squared_distance | Ran | xch-liu/geom-tex-dg/Dassl/dassl/metrics/distance.py code served (permissive licence) · get_code("4dae6b1e21e10987") |
| get_test_records | Ran | hlzhang109/ddg/model_selection.py code served (permissive licence) · get_code("53fac8d8d949e72b") |
| stage_path | Ran | hlzhang109/ddg/scripts/download.py code served (permissive licence) · get_code("c631ff42fed59f21") |
| compute_accuracy | Not yet run | xch-liu/geom-tex-dg/Dassl/dassl/metrics/accuracy.py code served (permissive licence) · get_code("da48cf51668411a0") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The problem of domain generalization is to learn from multiple training domains, and extract a domain-agnostic model that can then be applied to an unseen domain. Domain generalization (DG) has a clear motivation in contexts where there are target domains with distinct characteristics, yet sparse data for training. For example recognition in sketch images, which are distinctly more abstract and rarer than photos. Nevertheless, DG methods have primarily been evaluated on photo-only benchmarks focusing on alleviating the dataset bias where both problems of domain distinctiveness and data sparsity can be minimal. We argue that these benchmarks are overly straightforward, and show that simple deep learning baselines perform surprisingly well on them. In this paper, we make two main contributions: Firstly, we build upon the favorable domain shift-robust properties of deep learning methods, and develop a low-rank parameterized CNN model for end-to-end DG learning. Secondly, we develop a DG benchmark dataset covering photo, sketch, cartoon and painting domains. This is both more practically relevant, and harder (bigger domain shift) than existing benchmarks. The results show that our method outperforms existing DG alternatives, and our dataset provides a more significant DG challenge to drive future research.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1710.03077")
get_code_for_paper("1710.03077")
have("1710.03077")
Connect an agent — have() is free.