AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images

Sheng Guo, Weilin Huang, Haozhi Zhang, Chenfan Zhuang, Dengke Dong, Matthew R. Scott, Dinglong Huang

ECCV 2018 · Label-efficient and robust learning › Noisy labels · approach: Noisy cross-modal hashing and multi-label · 335 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
add the noisy subset as a second curriculum stage (ablation)CurriculumNet on BN-Inception · WebVision valtop-5 error: 12.98 -> 11.38Improved
add the highly noisy subset as a third curriculum stage (ablation)CurriculumNet on BN-Inception · WebVision valtop-5 error: 11.38 -> 10.82Improved
use the 3-subset curriculum instead of training on all data directly (ablation)CurriculumNet on BN-Inception · WebVision valtop-1 error: 30.16 -> 27.91Improved
use the 3-subset curriculum instead of training on all data directly (ablation)CurriculumNet on BN-Inception · WebVision valtop-5 error: 12.43 -> 10.82Improved
use the 3-subset curriculum instead of training on all data directly (ablation)CurriculumNet on BN-Inception · ImageNet val (trained on WebVision)top-5 error: 16.20 -> 15.11Improved
train on the clean subset only instead of all data (ablation)BN-Inception · WebVision valtop-5 error: 12.43 -> 12.98Hurt
use 50% of the highly noisy subset instead of 0% (ablation)Model-D · WebVision valtop-5 error: 11.38 -> 10.82Improved
increase highly noisy data from 50% to 100% (ablation)Model-D · WebVision valtop-5 error: 10.82 -> 10.94No clear effect
use density-based clustering instead of K-means for the curriculum (ablation)CurriculumNet Model-D · WebVision valtop-5 error: 16.6 -> 11.5No clear effect
use Inception_v3 instead of Inception_v2 (ablation)CurriculumNet Model-D · WebVision valtop-5 error: 10.82 -> 7.88Improved
use Inception_resnet_v2 instead of Inception_v3 (ablation)CurriculumNet Model-D · WebVision valtop-5 error: 7.88 -> 6.38Improved
add multi-scale 5x5, 7x7, 9x9 kernels in the first conv layer (ablation)BN-Inception · WebVision valtop-5 error: about 0.5%Improved

Later papers that compared with this method

4 later accepted papers report CurriculumNet as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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