Papers › Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning

Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning

8 Aug 2023ICCV 2023 1arXiv:2308.04016archive 2025-07-28

Hanjae Kim, Jiyoung Lee, Seongheon Park, Kwanghoon Sohn

Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior knowledge of known primitives (attribute and object). Previous works for CZSL often suffer from grasping the contextuality between attribute and object, as well as the discriminability of visual features, and the long-tailed distribution of real-world compositional data. We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. CoT employs object and attribute experts in distinctive manners to generate representative embeddings, using the visual network hierarchically. The object expert extracts representative object embeddings from the final layer in a bottom-up manner, while the attribute expert makes attribute embeddings in a top-down manner with a proposed object-guided attention module that models contextuality explicitly. To remedy biased prediction caused by imbalanced data distribution, we develop a simple minority attribute augmentation (MAA) that synthesizes virtual samples by mixing two images and oversampling minority attribute classes. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL. We also demonstrate the effectiveness of CoT in improving visual discrimination and addressing the model bias from the imbalanced data distribution. The code is available at https://github.com/HanjaeKim98/CoT.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.04016")

Code

Syntology Ran 11 of 12 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 7 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hanjaekim98/cot officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 11 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
2ran · fixture could not drive it
7ran
1unverified

Licence: 12 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hanjaekim98/cot. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

as_tuple hanjaekim98/cot/models/vit_utils.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 91d26d98a8c2bcac · report
calculate_mean_std hanjaekim98/cot/utils/utils.py official repository ran fingerprinted no licence file found · pointer only · 77dc755eec4b339c · report
cross_entropy_loss hanjaekim98/cot/models/cot.py official repository ran fingerprinted no licence file found · pointer only · 86116ff1c363bbaf · report
drop_head_variant hanjaekim98/cot/models/configs.py official repository ran · our draft was wrong no licence file found · pointer only · 940661961d8b8781 · report
imagenet_transform hanjaekim98/cot/dataset.py official repository ran no licence file found · pointer only · 808faf881ac6c7d4 · report
imagenet_transform_zappos hanjaekim98/cot/dataset.py official repository ran no licence file found · pointer only · c6872fbfb83dc783 · report
load_pretrained_weights hanjaekim98/cot/models/vit_utils.py official repository ran no licence file found · pointer only · 4cb49866c5980797 · report
merge_last hanjaekim98/cot/models/vit_transformer.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · d5e69fc7b0ee7c8c · report
reshape_text_features_to_concat hanjaekim98/cot/utils/utils.py official repository ran no licence file found · pointer only · 68994a7ec705cdf0 · report
resize_positional_embedding_ hanjaekim98/cot/models/vit_utils.py official repository ran no licence file found · pointer only · 6996b83764f078e7 · report
split_last hanjaekim98/cot/models/vit_transformer.py official repository ran · fixture could not drive it no licence file found · pointer only · a4a5354a3138c8ef · report
load_word_embeddings hanjaekim98/cot/models/word_embedding_utils.py official repository unverified no licence file found · pointer only · 020abdfee6c97495 · report

Tasks

AttributeCompositional Zero-Shot LearningObjectZero-Shot Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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