AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

AM-LFS: AutoML for Loss Function Search

Chuming Li, Xin Yuan, Chen Lin, Minghao Guo, Wei Wu, Junjie Yan, Wanli Ouyang

ICCV 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking-based loss optimization · 67 citations (OpenAlex)

Read the paperCheck 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
replace cross-entropy with AM-LFSResNet-20 · CIFAR-10top-1 error (%): 8.75 -> 6.92Improved
replace L2T-DLF with AM-LFSResNet-20 · CIFAR-10top-1 error (%): 7.63 -> 6.92Improved
replace cross-entropy with AM-LFS under 10% label noiseResNet-20 · CIFAR-10 (10% noise)top-1 error (%): 12.05 -> 10.05Improved
replace cross-entropy with AM-LFS under 20% label noiseResNet-20 · CIFAR-10 (20% noise)top-1 error (%): 15.05 -> 12.73Improved
replace ArcFace loss with AM-LFSResNet-20 · MegaFacerank1@1e6 (%): 72.4 -> 73.5Improved
add AM-LFS to MGN(RK)MGN(RK) · Market-1501mAP (%): 94.2 -> 94.6Improved
add AM-LFS to MGN(RK)MGN(RK) · Market-1501rank-1 (%): 96.6 -> 96.1Hurt
add AM-LFS to MGN(RK)MGN(RK) · DukeMTMC-reIDmAP (%): 88.6 -> 90.1Improved
add the search space with random sampling (no distribution update) to SphereReID (ablation)SphereReID · Market-1501mAP (%): 83.6 -> 84.0Improved
add optimization of the loss distribution on top of fixed-distribution sampling (ablation)AM-LFS (SphereReID) · Market-1501mAP (%): 84.0 -> 84.4Improved
increase number of samples B from 4 to 32 (ablation)AM-LFS (SphereReID) · Market-1501mAP (%): 83.6 -> 84.4Improved
increase number of samples B from 4 to 32 (ablation)AM-LFS (SphereReID) · DukeMTMC-reIDmAP (%): 68.4 -> 69.8Improved

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