SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.08666 · 2020

Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 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.

RepositoryRoleRan
virajprabhu/clue canonical 5 of 10
FunctionStatusWhere it lives
kmeans_plus_plus_opt Ran virajprabhu/clue/utils.py
code served (permissive licence) · get_code("887ef76a0f0b84bd")
outer_product_opt Ran virajprabhu/clue/utils.py
code served (permissive licence) · get_code("e331f59f46d29459")
process_txt Ran virajprabhu/clue/preprocess_domainnet.py
code served (permissive licence) · get_code("6962ebebbe6f9056")
register_model Ran virajprabhu/clue/adapt/models/models.py
code served (permissive licence) · get_code("8fadf1baab2bb38b")
register_solver Ran virajprabhu/clue/adapt/solvers/solver.py
code served (permissive licence) · get_code("b6020de74b4ef8f6")
get_model Not yet run virajprabhu/clue/adapt/models/models.py
code served (permissive licence) · get_code("2efe87863253f8ba")
get_solver Not yet run virajprabhu/clue/adapt/solvers/solver.py
code served (permissive licence) · get_code("6a049409bc8f279e")
get_strategy Not yet run virajprabhu/clue/sample.py
code served (permissive licence) · get_code("dbcd7c2c6017db5f")
register_strategy Not yet run virajprabhu/clue/sample.py
code served (permissive licence) · get_code("37dd93cc2f3a2f57")
row_norms Not yet run virajprabhu/clue/utils.py
code served (permissive licence) · get_code("dfb55f13a69a3302")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Generalizing deep neural networks to new target domains is critical to their real-world utility. In practice, it may be feasible to get some target data labeled, but to be cost-effective it is desirable to select a maximally-informative subset via active learning (AL). We study the problem of AL under a domain shift, called Active Domain Adaptation (Active DA). We demonstrate how existing AL approaches based solely on model uncertainty or diversity sampling are less effective for Active DA. We propose Clustering Uncertainty-weighted Embeddings (CLUE), a novel label acquisition strategy for Active DA that performs uncertainty-weighted clustering to identify target instances for labeling that are both uncertain under the model and diverse in feature space. CLUE consistently outperforms competing label acquisition strategies for Active DA and AL across learning settings on 6 diverse domain shifts for image classification.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2010.08666")
get_code_for_paper("2010.08666")
have("2010.08666")

Connect an agent — have() is free.