Attribute Aware Filter-Drop for Bias-Invariant Classification

Shruti Nagpal · Maneet Singh · Richa Singh · Mayank Vatsa A

19 citations0/0 files storedIEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Ethics and Social Impacts of AI Face recognition and analysis Domain Adaptation and Few-Shot Learning

Abstract

The widespread applicability of deep learning based algorithms demands dedicated attention towards ensuring unbiased behavior. Biased feature learning (for or against a particular sub-group) might often result in unfair predictions. In order to address the above issue, this research proposes a novel Filter-Drop algorithm for learning unbiased representations. The proposed technique focuses on learning the features useful for predicting the biasing attribute (or the sensitive attribute), followed by their elimination while performing the primary classification task. To this effect, a multi-task network is trained, which prevents the features capturing the attribute variations from being used for the primary classification task. The efficacy of the proposed Filter-Drop technique is demonstrated on two facial analysis datasets: UTKFace dataset and FairFace dataset. The proposed technique achieves similar performance across different ethnicity groups while training with highly skewed training data as well.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 19 citations exist upstream.

References

2018Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification 2018Mitigating Unwanted Biases with Adversarial Learning 2013Learning Fair Representations 2020Mitigating bias in algorithmic hiring 2015Fairness Constraints: Mechanisms for Fair Classification 2018Women Also Snowboard: Overcoming Bias in Captioning Models 2018Learning Adversarially Fair and Transferable Representations 2019Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations

Cited by

2021Attention Aware Debiasing for Unbiased Model Prediction

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.