AI Paper Atlas

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

Learning with Biased Complementary Labels

Xiyu Yu, Tongliang Liu, Mingming Gong, Dacheng Tao

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 192 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 estimated transition matrix instead of the true one (ablation)LM · CIFAR10 (uniform)accuracy (%): 73.38 -> 42.96Hurt
use the estimated transition matrix instead of the true one (ablation)LM · CIFAR10 (with0)accuracy (%): 85.32 -> 84.60No clear effect
use the estimated transition matrix instead of the true one (ablation)LM · MNIST (three settings)accuracy (%): 98.63 -> 98.61No clear effect
model biased (non-uniform) complementary labels with a transition matrix, versus the uniform assumption PC/SLM · CIFAR10 (with0)accuracy (%): 18.12 -> 85.32Improved
replace PC/S with LM under the uniform settingLM/T · MNIST (uniform)accuracy (%): 86.59 -> 97.18Improved
complementary labels drawn from a small subset of classes (with0) rather than uniformlyLM/T · CIFAR10accuracy (%): 73.38 -> 85.32Improved
complementary labels drawn from a small subset of classes (with0) rather than uniformlyLM/T · MNISTaccuracy (%): 97.18 -> 98.63Improved
use a non-invertible transition matrix instead of an invertible one (ablation)LM/T · MNIST (with0)accuracy (%): 98.63 -> 98.65No clear effect
use a manually designed Q instead of a randomly generated one (ablation)LM/T · MNIST (without0)accuracy (%): 97.65 -> 97.15No clear effect
use a manually designed Q instead of a randomly generated one (ablation)LM/T · MNIST (with0)accuracy (%): 98.63 -> 98.56No clear effect
replace PC/S with LM on CIFAR100LM/T · CIFAR100 (with0)accuracy (%): 8.95 -> 62.84Improved
replace PC/S with LM on UCI PENDIGITS, all 10 classesLM · PENDIGITS (classes 1 ~ 10)accuracy (%): 38.0 -> 62.8Improved

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