Mitchell Wortsman, Ali Farhadi, Simon Kornblith, Hannaneh Hajishirzi, Gabriel Ilharco, Rebecca Roelofs, Ludwig Schmidt, Raphael Gontijo-Lopes, Hongseok Namkoong, Mike Li, Jong Kim
We lifted 3 functions out of this paper's own repositories and ran 1 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 |
|---|---|---|
| mlfoundations/wise-ft | — | 1 of 1 |
| mlfoundations/model-soups | — | 0 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| _merge | Ran | mlfoundations/wise-ft/src/wise_ft.py pointer only (licence: NOASSERTION) · get_code("55033a7e690ca43b") |
| AlphaWrapper | Not yet run | mlfoundations/model-soups/learned_bylayer.py code served (permissive licence) · get_code("602d9712f9f7e7ee") |
| load_weights | Not yet run | mlfoundations/model-soups/learned_bylayer.py code served (permissive licence) · get_code("52e1473acbb0e1fb") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of data distributions when performing zero-shot inference (i.e., without fine-tuning on a specific dataset). Although existing fine-tuning methods substantially improve accuracy on a given target distribution, they often reduce robustness to distribution shifts. We address this tension by introducing a simple and effective method for improving robustness while fine-tuning: ensembling the weights of the zero-shot and fine-tuned models (WiSE-FT). Compared to standard fine-tuning, WiSE-FT provides large accuracy improvements under distribution shift, while preserving high accuracy on the target distribution. On ImageNet and five derived distribution shifts, WiSE-FT improves accuracy under distribution shift by 4 to 6 percentage points (pp) over prior work while increasing ImageNet accuracy by 1.6 pp. WiSE-FT achieves similarly large robustness gains (2 to 23 pp) on a diverse set of six further distribution shifts, and accuracy gains of 0.8 to 3.3 pp compared to standard fine-tuning on seven commonly used transfer learning datasets. These improvements come at no additional computational cost during fine-tuning or inference.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.01903")
get_code_for_paper("2109.01903")
have("2109.01903")
Connect an agent — have() is free.