Skip to main content
andrewliao11
Projects
knn_crowdsourcing
Reports
Project
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Reports
Created by
Created On
Last edited
Performance plot
0
andrewliao11
2020-11-09
Experiment on all setting
0
andrewliao11
2020-11-06
Different features
0
andrewliao11
2020-11-02
Algorithm Compare
0
andrewliao11
2020-11-02
Lower maximum annotation number
0
andrewliao11
2020-11-02
Compare pseudolabel
0
andrewliao11
2020-10-31
Ensure enough data in training set
0
andrewliao11
2020-10-31
ImageNet100 classes
0
andrewliao11
2020-10-31
Temperature clean and Temperature clean grow
0
andrewliao11
2020-10-31
Stopping criterion to be the likelihood change
0
andrewliao11
2020-10-29
Compare PseudoLabel (fixed)
0
andrewliao11
2020-10-30
Comparing Pseudo label
0
andrewliao11
2020-10-30
Comparing prior strength
0
andrewliao11
2020-10-29
Reset learners with warmup
0
andrewliao11
2020-10-29
Reset the pseudo label
0
andrewliao11
2020-10-28
Avoid Sample too many annotation for certain examples
0
andrewliao11
2020-10-28
Worker Construction vs. priors
0
andrewliao11
2020-10-27
Compare with Lean
0
andrewliao11
2020-10-27
Compare PseudoLabel and LeanPseudoLabel
0
andrewliao11
2020-10-27
Prior vs. Simulated Worker Construction
0
andrewliao11
2020-10-27
Different simulated worker construction
0
andrewliao11
2020-10-26
Different worker prior
0
andrewliao11
2020-10-26
Different worker initialization
0
andrewliao11
2020-10-26
Real Worker Initialization
0
andrewliao11
2020-10-25
Comparing real human workers and simulated ones
0
andrewliao11
2020-10-24
Compare PseudoLabel with Lean
0
andrewliao11
2020-10-22
Update graph with negative pair or not
0
andrewliao11
2020-10-19
Oct.14
0
andrewliao11
2020-10-14
SVM vs. LP
0
andrewliao11
2020-10-18
Varying batch size
0
andrewliao11
2020-10-19
A minor change in EM procedure matters a lot
0
andrewliao11
2020-10-13
Oct. 10
0
andrewliao11
2020-10-10
Large-scale Experiments
0
andrewliao11
2020-10-05
Ablation Study
0
andrewliao11
2020-09-21
Untitled Report
0
andrewliao11
2020-09-14
Kcenter vs. Random
0
andrewliao11
2020-09-11
Worker calibration
0
andrewliao11
2020-09-10
Estimating worker skills
0
andrewliao11
2020-09-07
Label Propagation vs. LinearSVM
0
andrewliao11
2020-08-19
Robustness Check
0
andrewliao11
2020-08-21
Hierarchical accuracy
0
andrewliao11
2020-08-14
Uniform vs. Semantic workers
0
andrewliao11
2020-08-11
Contribution of worker and cv
0
andrewliao11
2020-08-07
rank plot
0
andrewliao11
2020-08-06
PCA results
0
andrewliao11
2020-08-03
Top 1, 5, 10 accuracy
0
andrewliao11
2020-07-28
Google engine as additional labeled image sources
0
andrewliao11
2020-07-28
Practical crowdsourcing (w/ stopping criterion)
Practical crowdsourcing should monitor the confidence of the label and set the stopping criterion.
0
andrewliao11
2020-07-22
Efficient plot
0
andrewliao11
2020-07-19
Online Efficient Plot
0
andrewliao11
2020-07-14
Bayes+linearSVM, Bayes+k-NN
The worker here has the same average (over classes) reliability. The results show that k-NN sometimes beat linearSVM, especially when the risk threshold is low (=0.)
0
andrewliao11
2020-07-10
Noisy Workers
0
andrewliao11
2020-07-13