AI Paper Atlas

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

Matrix Tri-Factorization With Manifold Regularizations for Zero-Shot Learning

CVPR 2017 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 136 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
add joint test-time manifold prediction (ablation)MFMR · aPY, AwA, CUB, and SUNaccuracy (%): 48.2 -> 56.8; 79.8 -> 83.5; 47.7 -> 53.6; 84.0 -> 84.5Helped
add joint test-time manifold prediction (ablation)MFMR · aPY, AwA, CUB, and SUNmAP (%): 45.6 -> 55.9; 70.8 -> 82.8; 30.6 -> 47.5; 77.4 -> 83.2Helped
add joint test-time manifold prediction (ablation)MFMR · AwA generalized ZSLU → T accuracy: 13.4 -> 18.4Helped
vary manifold regularization coefficient λ (ablation)MFMR and MFMR-joint · AwA and CUBaccuracy (%)Mixed
vary neighborhood parameter k (ablation)MFMR and MFMR-joint · AwA and CUBaccuracy (%)Mixed
increase test-instance manifold coefficient γ (ablation)MFMR-joint · AwA and CUBaccuracy (%)Helped

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