</> Code with Papers by Syntology

Datasets › MIT-States

MIT-States

Introduced by Phillip Isola et al. in Discovering States and Transformations in Image Collections1 Jan 2015 archive 2025-07-28

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

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Retrieval with Multi-Modal Query MIT-States ComposeAE Recall@1 13.9 Compositional Learning of Image-Text Query for Image Retrieval ecom-research/ComposeAE 5 Compare
Compositional Zero-Shot Learning MIT-States CANet AUC 5.4 Learning Conditional Attributes for Compositional... wqshmzh/canet-czsl 2 Compare
Compositional Zero-Shot Learning MIT-States, generalized split CAILA H-Mean 39.9 CAILA: Concept-Aware Intra-Layer Adapters for... zhaohengz/llamp +1 2 Compare
Zero-Shot Learning MIT-States CZSL A-acc 36.0 LOCL: Learning Object-Attribute Composition using Localization satish1901/LOCL-Learning-Object-Attribute-Composition-using-Localization 1 Compare

Papers archive 2025-07-28

9 shown of 9 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 91. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Learning Conditional Attributes for Compositional Zero-Shot Learning 1 1 29 May 2023 ran 6 of 9 samples (3 unverified; 9 pointer-only for licence)
CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning 2 1 26 May 2023 not harvested
LOCL: Learning Object-Attribute Composition using Localization 1 1 7 Oct 2022 not harvested
Compositional Learning of Image-Text Query for Image Retrieval 1 1 19 Jun 2020 ran 0 of 1 samples (1 unverified)
Symmetry and Group in Attribute-Object Compositions 1 2 1 Apr 2020 not harvested
Composing Text and Image for Image Retrieval - An Empirical Odyssey 4 1 18 Dec 2018 ran 0 of 1 samples (1 unverified)
Attributes as Operators: Factorizing Unseen Attribute-Object Compositions 1 1 27 Mar 2018 ran 0 of 3 samples (3 unverified)
FiLM: Visual Reasoning with a General Conditioning Layer 7 1 22 Sep 2017 ran 9 of 10 samples (1 unverified; 7 pointer-only for licence)
Show and Tell: A Neural Image Caption Generator 74 1 17 Nov 2014 ran 13 of 34 samples (21 unverified; 6 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Zero-Shot LearningImage Retrieval with Multi-Modal QueryCompositional Zero-Shot Learning

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • MIT-States
  • MIT-States, generalized split

2 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections