SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.04521 · 2023

GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 16 functions out of this paper's own repositories and ran 13 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
atsumiyai/gl-mcm canonical 13 of 16
FunctionStatusWhere it lives
accuracy Ran atsumiyai/gl-mcm/utils/common.py
code served (permissive licence) · get_code("088e80bb4051265a")
basic_clean Ran atsumiyai/gl-mcm/clip/simple_tokenizer.py
code served (permissive licence) · get_code("98f385d847636a3e")
fpr_and_fdr_at_recall Ran atsumiyai/gl-mcm/utils/detection_util.py
code served (permissive licence) · get_code("3853ecdb6fc74451")
get_pairs Ran atsumiyai/gl-mcm/clip/simple_tokenizer.py
code served (permissive licence) · get_code("d919ae32e5e4e616")
get_subset_with_len Ran atsumiyai/gl-mcm/utils/train_eval_util.py
code served (permissive licence) · get_code("80c8dac5a9baef31")
get_test_labels Ran atsumiyai/gl-mcm/utils/common.py
code served (permissive licence) · get_code("75e589009e3da37c")
load_scores Ran atsumiyai/gl-mcm/utils/file_ops.py
code served (permissive licence) · get_code("2358075eb310a541")
prepare_dataframe Ran atsumiyai/gl-mcm/utils/file_ops.py
code served (permissive licence) · get_code("1be3e6a03938ec75")
read_file Ran atsumiyai/gl-mcm/utils/common.py
code served (permissive licence) · get_code("65aed69fd9c43272")
set_val_loader Ran atsumiyai/gl-mcm/utils/train_eval_util.py
code served (permissive licence) · get_code("f3fda6c7f479b606")
setup_log Ran atsumiyai/gl-mcm/utils/file_ops.py
code served (permissive licence) · get_code("db2eed8f505e7836")
stable_cumsum Ran atsumiyai/gl-mcm/utils/detection_util.py
code served (permissive licence) · get_code("d4acb3120a027622")
whitespace_clean Ran atsumiyai/gl-mcm/clip/simple_tokenizer.py
code served (permissive licence) · get_code("9542161e9640b858")
build_model Not yet run atsumiyai/gl-mcm/clip/model.py
code served (permissive licence) · get_code("a7667e7d84eccfd8")
get_measures Not yet run atsumiyai/gl-mcm/utils/detection_util.py
code served (permissive licence) · get_code("24570af601666d85")
load Not yet run atsumiyai/gl-mcm/clip/clip.py
code served (permissive licence) · get_code("c22a78c25372b59f")

Repositories linked to this paper

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

Abstract

Zero-shot out-of-distribution (OOD) detection is a task that detects OOD images during inference with only in-distribution (ID) class names. Existing methods assume ID images contain a single, centered object, and do not consider the more realistic multi-object scenarios, where both ID and OOD objects are present. To meet the needs of many users, the detection method must have the flexibility to adapt the type of ID images. To this end, we present Global-Local Maximum Concept Matching (GL-MCM), which incorporates local image scores as an auxiliary score to enhance the separability of global and local visual features. Due to the simple ensemble score function design, GL-MCM can control the type of ID images with a single weight parameter. Experiments on ImageNet and multi-object benchmarks demonstrate that GL-MCM outperforms baseline zero-shot methods and is comparable to fully supervised methods. Furthermore, GL-MCM offers strong flexibility in adjusting the target type of ID images. The code is available via https://github.com/AtsuMiyai/GL-MCM.

For agents

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

get_harvested_code_for_paper("2304.04521")
get_code_for_paper("2304.04521")
have("2304.04521")

Connect an agent — have() is free.