UniShape
A shape-aware foundation model used as a frozen representation backbone for classification.
Using UniShape for time series classification
A shape-aware foundation model used as a frozen representation backbone for classification.
In this benchmark, UniShape is evaluated using frozen representation + fitted classifier. Checkpoint information: unishape_checkpoint_zeroshot.pth. Check the results below for the settings and dataset scopes with published scores.
Evaluated configurations
Classifier heads are grouped under their shared pretrained model here. They remain separate leaderboard entries because they are different experimental configurations.
- Organization
- SCUT · A*STAR · Khalifa University
- Parameters
- 3.1M backbone
- Checkpoint used
- unishape_checkpoint_zeroshot.pth
- Input Type
- Univariate + multivariate time series
- Inference
- Frozen representation + fitted classifier
UniShape classification benchmark results
Compare accuracy and average rank only within the same evaluation setting and dataset scope. Standard uses the official training splits; 5-shot and 10-shot use different budget-feasible subsets. Rank and average rank include other models in the full comparison set. Scores are not averaged across configurations.
For comparisons with other backbones, open the foundation model classification leaderboard and use the same setting and scope. The few-shot evaluation protocol explains the label budgets.
Standard · Overall
Comparison set: 12 configurations
This Standard time series classification comparison reports 1 UniShape configuration for the overall dataset scope. Each row shows its own coverage.
The highest reported average accuracy among this model's configurations in this setting is 76.87%, reported by UniShape+RF with coverage 198 / 198. This configuration ranks 3 of 12 in this comparison set. The result describes this configuration and setting, rather than every possible use of the pretrained model.
| Configuration | Overall Rank | Overall Accuracy (%) | Avg. Rank | Coverage |
|---|---|---|---|---|
| UniShape+RF | 3 | 76.87 | 5.08 | 198 / 198 |
Standard · Univariate
Comparison set: 19 configurations
This Standard time series classification comparison reports 1 UniShape configuration for the univariate dataset scope. Each row shows its own coverage.
The highest reported average accuracy among this model's configurations in this setting is 78.86%, reported by UniShape+RF with coverage 128 / 128. This configuration ranks 7 of 19 in this comparison set. The result describes this configuration and setting, rather than every possible use of the pretrained model.
| Configuration | Univariate Rank | Univariate Accuracy (%) | Avg. Rank | Coverage |
|---|---|---|---|---|
| UniShape+RF | 7 | 78.86 | 7.82 | 128 / 128 |
Standard · Multivariate
Comparison set: 12 configurations
This Standard time series classification comparison reports 1 UniShape configuration for the multivariate dataset scope. Each row shows its own coverage.
The highest reported average accuracy among this model's configurations in this setting is 73.22%, reported by UniShape+RF with coverage 70 / 70. This configuration ranks 3 of 12 in this comparison set. The result describes this configuration and setting, rather than every possible use of the pretrained model.
| Configuration | Multivariate Rank | Multivariate Accuracy (%) | Avg. Rank | Coverage |
|---|---|---|---|---|
| UniShape+RF | 3 | 73.22 | 5.04 | 70 / 70 |
UniShape paper, code and checkpoint
- PaperOpen official resource
- CodeOpen official resource
- CheckpointOpen official resource
Reading this model's evaluation
The method catalog describes the pretrained model; leaderboard eligibility depends on the actual coverage of each experimental configuration. Catalog inclusion does not imply complete coverage of all 198 datasets.