pith. sign in

arxiv: 2103.06179 · v1 · pith:RVUDF7BAnew · submitted 2021-03-10 · 💻 cs.CV · cs.AI

Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing

classification 💻 cs.CV cs.AI
keywords biasclassifierdatasetfeaturesimageslearningtrainingadversarial
0
0 comments X
read the original abstract

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset, frequently caused by the co-occurrence of relevant features and irrelevant ones. To mitigate this issue, we require learning algorithms that prevent the propagation of bias from the dataset into the classifier. We present a novel adversarial debiasing method, which addresses a feature that is spuriously connected to the labels of training images but statistically independent of the labels for test images. Thus, the automatic identification of relevant features during training is perturbed by irrelevant features. This is the case in a wide range of bias-related problems for many computer vision tasks, such as automatic skin cancer detection or driver assistance. We argue by a mathematical proof that our approach is superior to existing techniques for the abovementioned bias. Our experiments show that our approach performs better than state-of-the-art techniques on a well-known benchmark dataset with real-world images of cats and dogs.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution

    cs.AI 2026-05 unverdicted novelty 6.0

    Causality provides a unifying framework for resolving trade-offs in trustworthy AI by managing invariance conflicts under changes to the data-generating process.

  2. Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution

    cs.AI 2026-05 unverdicted novelty 4.0

    Causality resolves trade-offs in trustworthy AI by treating them as invariance conflicts under different data-generating process changes.