Stella X. Yu : Papers / Google Scholar

Debiased Learning from Naturally Imbalanced Pseudo-Labels
Xudong Wang and Zhirong Wu and Long Lian and Stella X. Yu
IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, Louisiana, 19-24 June 2022
Paper | Slides | Code | arXiv

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting.

Our key insight is that pseudo-labels are naturally imbalanced due to intrinsic data similarity, even when a model is trained on balanced source data and evaluated on balanced target data. If we address this previously unknown imbalanced classification problem arising from pseudo-labels instead of ground-truth training labels, we could remove model biases towards false majorities created by pseudo-labels.

We propose a novel and effective debiased learning method with pseudo-labels, based on counterfactual reasoning and adaptive margins: The former removes the classifier response bias, whereas the latter adjusts the margin of each class according to the imbalance of pseudo-labels. Validated by extensive experimentation, our simple debiased learning delivers significant accuracy gains over the state-of-the-art on ImageNet-1K: 26\% for semi-supervised learning with 0.2\% annotations and 9\% for zero-shot learning. Our code is available at: \url{}.

debiased learning, imbalanced classification, semi-supervised learning