Papers › Symmetry and Group in Attribute-Object Compositions

Symmetry and Group in Attribute-Object Compositions

1 Apr 2020CVPR 2020 6arXiv:2004.00587archive 2025-07-28

Yong-Lu Li, Yue Xu, Xiaohan Mao, Cewu Lu

Attributes and objects can compose diverse compositions. To model the compositional nature of these general concepts, it is a good choice to learn them through transformations, such as coupling and decoupling. However, complex transformations need to satisfy specific principles to guarantee the rationality. In this paper, we first propose a previously ignored principle of attribute-object transformation: Symmetry. For example, coupling peeled-apple with attribute peeled should result in peeled-apple, and decoupling peeled from apple should still output apple. Incorporating the symmetry principle, a transformation framework inspired by group theory is built, i.e. SymNet. SymNet consists of two modules, Coupling Network and Decoupling Network. With the group axioms and symmetry property as objectives, we adopt Deep Neural Networks to implement SymNet and train it in an end-to-end paradigm. Moreover, we propose a Relative Moving Distance (RMD) based recognition method to utilize the attribute change instead of the attribute pattern itself to classify attributes. Our symmetry learning can be utilized for the Compositional Zero-Shot Learning task and outperforms the state-of-the-art on widely-used benchmarks. Code is available at https://github.com/DirtyHarryLYL/SymNet.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

DirtyHarryLYL/SymNet officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Single/Multi-Attribute of Object with Symmetry and Group (arXiv:2110.04603; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AttributeCompositional Zero-Shot LearningObjectZero-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Compositional Zero-Shot Learning MIT-States SymNet Top-1 accuracy % 19.9 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States SymNet Top-2 accuracy % 28.2 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States SymNet Top-3 accuracy % 33.8 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States, generalized split SymNet H-Mean 16.1 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States, generalized split SymNet Seen accuracy 24.4 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States, generalized split SymNet Test AUC top 1 3.0 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States, generalized split SymNet Test AUC top 2 7.6 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States, generalized split SymNet Test AUC top 3 12.3 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States, generalized split SymNet Unseen accuracy 25.2 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States, generalized split SymNet Val AUC top 1 4.3 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States, generalized split SymNet Val AUC top 2 9.8 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning MIT-States, generalized split SymNet Val AUC top 3 14.8 #2 of 2 Archive leaderboard report
Compositional Zero-Shot Learning UT-Zappos SymNet Top-1 accuracy % 52.1 #1 of 1 Archive leaderboard report
Compositional Zero-Shot Learning UT-Zappos SymNet Top-2 accuracy % 67.8 #1 of 1 Archive leaderboard report
Compositional Zero-Shot Learning UT-Zappos SymNet Top-3 accuracy % 76.0 #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.

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