TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/MIT-States

MIT-States

ImagesUnknownIntroduced 2015-01-01

The MIT-States dataset has 245 object classes, 115 attribute classes and ∼53K images. There is a wide range of objects (e.g., fish, persimmon, room) and attributes (e.g., mossy, deflated, dirty). On average, each object instance is modified by one of the 9 attributes it affords.

Source: Attributes as Operators: Factorizing Unseen Attribute-Object Compositions Image Source: http://web.mit.edu/phillipi/Public/states_and_transformations/index.html

Benchmarks

Image Retrieval with Multi-Modal Query/Recall@1Image Retrieval with Multi-Modal Query/Recall@5Image Retrieval with Multi-Modal Query/Recall@10Zero-Shot Learning/A-accZero-Shot Learning/AUCZero-Shot Learning/Attribute accuracyZero-Shot Learning/Object accuracyZero-Shot Learning/Seen accuracyZero-Shot Learning/Top-1 accuracy %Zero-Shot Learning/Top-2 accuracy %Zero-Shot Learning/Top-3 accuracy %Zero-Shot Learning/Unseen accuracyZero-Shot Learning/best HM

Related Benchmarks

MIT-States, generalized split/Zero-Shot Learning/H-MeanMIT-States, generalized split/Zero-Shot Learning/Seen accuracyMIT-States, generalized split/Zero-Shot Learning/Test AUC top 1MIT-States, generalized split/Zero-Shot Learning/Test AUC top 2MIT-States, generalized split/Zero-Shot Learning/Test AUC top 3MIT-States, generalized split/Zero-Shot Learning/Unseen accuracyMIT-States, generalized split/Zero-Shot Learning/Val AUC top 1MIT-States, generalized split/Zero-Shot Learning/Val AUC top 2MIT-States, generalized split/Zero-Shot Learning/Val AUC top 3

Statistics

Papers
91
Benchmarks
13

Links

Homepage

Tasks

Compositional Zero-Shot LearningImage Retrieval with Multi-Modal QueryZero-Shot Learning