AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l1-Norm Distances

Kai Liu, Hua Wang, Feiping Nie, Hao Zhang

CVPR 2018 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 17 citations (OpenAlex)

Read the paper

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
Use the multi-instance enriched representation with SVM instead of the strongest baselineOur method (SVM) · PASCAL VOC 2010Hamming loss: 0.173 ± 0.011 -> 0.155 ± 0.014Improved
Use the multi-instance enriched representation with SVM instead of the strongest baselineOur method (SVM) · PASCAL VOC 2010One-error: 0.306 ± 0.018 -> 0.272 ± 0.011Improved
Use the multi-instance enriched representation with SVM instead of the strongest baselineOur method (SVM) · PASCAL VOC 2010Average precision: 0.485 ± 0.022 -> 0.507 ± 0.015Improved
Use the multi-instance enriched representation with SVM instead of the strongest baselineOur method (SVM) · Corel5KHamming loss: 0.238 ± 0.004 -> 0.204 ± 0.015Improved
Use the multi-instance enriched representation with SVM instead of the strongest baselineOur method (SVM) · Corel5KAverage precision: 0.559 ± 0.018 -> 0.604 ± 0.010Improved
Use the multi-instance enriched representation with SVM instead of the strongest baselineOur method (SVM) · SceneHamming loss: 0.215 ± 0.011 -> 0.175 ± 0.004Improved
Use the multi-instance enriched representation with SVM instead of the strongest baselineOur method (SVM) · SceneOne-error: 0.370 ± 0.012 -> 0.355 ± 0.016Improved
Use the multi-instance enriched representation with SVM instead of the strongest baselineOur method (SVM) · SceneAverage precision: 0.715 ± 0.033 -> 0.794 ± 0.011Improved

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