AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Labels, Information, and Computation: Efficient Learning Using Sufficient Labels

Shiyu Duan, Spencer Chang, Jose C. Principe

JMLR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 5 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
double sufficient pairs from 120k to 240k (ablation)sufficient-label learning, hinge, 10 full labels · MNISTtest accuracy (%): 98.97 -> 99.12Improved
double sufficient pairs from 100k to 200k (ablation)sufficient-label learning, hinge, 10 full labels · CIFAR-10test accuracy (%): 90.99 -> 93.56Improved
use online sufficient pair sampling instead of fixed 200k pairs (ablation)sufficient-label learning, hinge · CIFAR-10test accuracy (%): 93.56 -> 94.24Improved
double sufficient pairs from 146,514 to 293,028 (ablation)sufficient-label learning, hinge · SVHNtest accuracy (%): 95.77 -> 96.11Improved
double sufficient pairs from 400k to 800k (ablation)sufficient-label learning, hinge, 100 full labels · CIFAR-100test accuracy (%): 70.45 -> 72.67Improved
replace 50k full labels with online sufficient labels plus 10 full labelsLeNet-5 hinge · MNISTtest accuracy (%): 99.22 -> 99.23No clear effect
replace 73,257 full labels with online sufficient labels plus 10 full labelsResNet-18 hinge · SVHNtest accuracy (%): 96.49 -> 96.66Improved
replace 50k full labels with online sufficient labels plus 10 full labelsResNet-18 hinge · CIFAR-10test accuracy (%): 94.09 -> 94.24Improved
replace 60k full labels with online sufficient labels plus 10 full labelsResNet-18 cross-entropy · Fashion-MNISTtest accuracy (%): 95.10 -> 95.03Hurt
replace 50k full labels with online sufficient labels plus 100 full labelsResNet-18 cross-entropy · CIFAR-100test accuracy (%): 74.18 -> 73.98Hurt
replace 50k full labels with online sufficient labels plus 100 full labelsResNet-18 hinge · CIFAR-100test accuracy (%): 73.22 -> 73.79Improved
use fixed 120k sufficient pairs plus 10 full labels instead of 60k full labelsLeNet-5 cross-entropy · MNISTtest accuracy (%): 99.32 -> 98.98Hurt

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