Papers › Learning Conditional Attributes for Compositional Zero-Shot Learning

Learning Conditional Attributes for Compositional Zero-Shot Learning

29 May 2023CVPR 2023 1arXiv:2305.17940archive 2025-07-28

Qingsheng Wang, Lingqiao Liu, Chenchen Jing, Hao Chen, Guoqiang Liang, Peng Wang, Chunhua Shen

Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations. One of the challenges is to model attributes interacted with different objects, e.g., the attribute ``wet" in ``wet apple" and ``wet cat" is different. As a solution, we provide analysis and argue that attributes are conditioned on the recognized object and input image and explore learning conditional attribute embeddings by a proposed attribute learning framework containing an attribute hyper learner and an attribute base learner. By encoding conditional attributes, our model enables to generate flexible attribute embeddings for generalization from seen to unseen compositions. Experiments on CZSL benchmarks, including the more challenging C-GQA dataset, demonstrate better performances compared with other state-of-the-art approaches and validate the importance of learning conditional attributes. Code is available at https://github.com/wqshmzh/CANet-CZSL

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="2305.17940")

Code

Syntology Ran 6 of 9 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wqshmzh/canet-czsl officialmentioned in papermentioned on GitHubpytorch 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

9 samples harvested; 6 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · fixture could not drive it
4ran
3unverified

Licence: 9 of the 9 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 wqshmzh/canet-czsl. “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.

AttrAdapter wqshmzh/canet-czsl/model/CANet.py official repository ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 489268fd0cbaa517 · report
HyperNet wqshmzh/canet-czsl/model/CANet.py official repository ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · e3cdf2acc58d7856 · report
HyperNetStructure wqshmzh/canet-czsl/model/CANet.py official repository ran GPL-3.0 (copyleft) · pointer only · 86b1cab4e42f9138 · report
MLP wqshmzh/canet-czsl/model/CANet.py official repository ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 199c4a7179cfd0fe · report
load_fasttext_embeddings wqshmzh/canet-czsl/model/CANet.py official repository ran · fixture could not drive it GPL-3.0 (copyleft) · pointer only · 4d3bbc067a832537 · report
load_word2vec_embeddings wqshmzh/canet-czsl/model/CANet.py official repository ran · fixture could not drive it GPL-3.0 (copyleft) · pointer only · 8fdd4c546860a41a · report
CANet wqshmzh/canet-czsl/model/CANet.py official repository unverified GPL-3.0 (copyleft) · pointer only · 010039bf01818d17 · report
load_glove_embeddings wqshmzh/canet-czsl/model/CANet.py official repository unverified GPL-3.0 (copyleft) · pointer only · aba0a7e44b8a0d05 · report
load_word_embeddings wqshmzh/canet-czsl/model/CANet.py official repository unverified GPL-3.0 (copyleft) · pointer only · 6b5dc9727f0f6fc7 · report

Tasks

AttributeCompositional Zero-Shot LearningZero-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Compositional Zero-Shot Learning MIT-States CANet AUC 5.4 #1 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States CANet Attribute accuracy 30.2 #1 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States CANet Object accuracy 32.6 #1 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States CANet Seen accuracy 29 #1 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States CANet Unseen accuracy 26.2 #1 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States CANet best HM 17.9 #1 of 2 Archive leaderboard report
Compositional Zero-Shot Learning UT Zappos50K CANet AUC 33.1 #1 of 1 Archive leaderboard report
Compositional Zero-Shot Learning UT Zappos50K CANet Attribute accuracy 48.4 #1 of 1 Archive leaderboard report
Compositional Zero-Shot Learning UT Zappos50K CANet Object accuracy 72.6 #1 of 1 Archive leaderboard report
Compositional Zero-Shot Learning UT Zappos50K CANet Seen accuracy 61 #1 of 1 Archive leaderboard report
Compositional Zero-Shot Learning UT Zappos50K CANet Unseen accuracy 66.3 #1 of 1 Archive leaderboard report
Compositional Zero-Shot Learning UT Zappos50K CANet best HM 47.3 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

BASE

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