AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning

Shyamgopal Karthik, Massimiliano Mancini, Zeynep Akata

CVPR 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 70 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
predict states and objects separately rather than directly over compositions (ablation)CGE · MIT-States validation OW-CZSLHM: 7.0 -> 8.1Improved
add ConceptNet-based hard masking of infeasible compositions (ablation)KG-SP-ff · MIT-States validation OW-CZSLUnseen accuracy: 7.4 -> 7.7Improved
add ConceptNet-guided pseudo-labeling (ablation)KG-SP · MIT-States validation pCZSLHM: 4.8 -> 5.3Improved
replace knowledge-guided pseudo-labeling with vanilla pseudo-labeling (ablation)KG-SP · MIT-States validation pCZSLSeen accuracy: 16.6 vs 15.9Hurt
use Gumbel-softmax sampling without external feasibility knowledge (ablation)KG-SP · MIT-States validation pCZSLHM: 4.8 vs 4.5Hurt
increase classifier depth from 3 to 5 layers (ablation)KG-SP-ff · UT-Zappos validation OW-CZSLAUC: 26.9 to 24.3Hurt
add entropy minimization (ablation)CGE · C-GQA pCZSLAUC: 1.4 -> 1.8Improved
add entropy minimization (ablation)CGE · UT-Zappos pCZSLAUC: 10.7 -> 8.7Hurt
add pseudo-labeling (ablation)CompCos · MIT-States pCZSLAUC: 3.6 to 3.2Hurt
use ConceptNet feasibility scores instead of no masking (ablation)KG-SP-ff · MIT-States validation OW-CZSLHM: 7.9 -> 8.2Improved
use deeper nonlinear primitive classifiers instead of shallow predictors (ablation)KG-SP-ff · UT-Zappos and MIT-States validation OW-CZSLAUCImproved

Later papers that compared with this method

2 later accepted papers report KG-SP as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy