SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.07972 · 2022

Sparse Visual Counterfactual Explanations in Image Space

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 4 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
valentyn1boreiko/svces_code canonical 4 of 6
FunctionStatusWhere it lives
Cifar100Wrapper Ran valentyn1boreiko/svces_code/utils/model_normalization.py
code served (permissive licence) · get_code("af14c4446f7cffb4")
Cifar10Wrapper Ran valentyn1boreiko/svces_code/utils/model_normalization.py
code served (permissive licence) · get_code("803b314109470237")
IdentityWrapper Ran valentyn1boreiko/svces_code/utils/model_normalization.py
code served (permissive licence) · get_code("bbdb58215a0e1a06")
get_filename Ran valentyn1boreiko/svces_code/utils/load_trained_model.py
code served (permissive licence) · get_code("7d476c2ca8c4113d")
build_model_big_transfer Not yet run valentyn1boreiko/svces_code/utils/models/big_transfer_factory.py
code served (permissive licence) · get_code("c0da9b2317282066")
get_TinyImageNetClassNames Not yet run valentyn1boreiko/svces_code/utils/datasets/tiny_image_net.py
code served (permissive licence) · get_code("16ac425097ec58cd")

Repositories linked to this paper

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

Abstract

Visual counterfactual explanations (VCEs) in image space are an important tool to understand decisions of image classifiers as they show under which changes of the image the decision of the classifier would change. Their generation in image space is challenging and requires robust models due to the problem of adversarial examples. Existing techniques to generate VCEs in image space suffer from spurious changes in the background. Our novel perturbation model for VCEs together with its efficient optimization via our novel Auto-Frank-Wolfe scheme yields sparse VCEs which lead to subtle changes specific for the target class. Moreover, we show that VCEs can be used to detect undesired behavior of ImageNet classifiers due to spurious features in the ImageNet dataset.

For agents

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

get_harvested_code_for_paper("2205.07972")
get_code_for_paper("2205.07972")
have("2205.07972")

Connect an agent — have() is free.