[论文解读] Learning Debiased Representation via Disentangled Feature Augmentation

Jungsoo Lee, Eungyeup Kim+3 more|arXiv (Cornell University)|Jul 3, 2021

Domain Adaptation and Few-Shot Learning参考文献 35被引用 46

一句话总结

该论文提出一种特征级数据增强方法，通过解耦内在属性和偏置属性来合成多样的偏置冲突样本，从而提升偏差去除和在合成及真实数据集上的泛化能力。

ABSTRACT

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability when evaluated on unbiased datasets. Existing approaches for debiasing often identify and emphasize those samples with no such correlation (i.e., bias-conflicting) without defining the bias type in advance. However, such bias-conflicting samples are significantly scarce in biased datasets, limiting the debiasing capability of these approaches. This paper first presents an empirical analysis revealing that training with "diverse" bias-conflicting samples beyond a given training set is crucial for debiasing as well as the generalization capability. Based on this observation, we propose a novel feature-level data augmentation technique in order to synthesize diverse bias-conflicting samples. To this end, our method learns the disentangled representation of (1) the intrinsic attributes (i.e., those inherently defining a certain class) and (2) bias attributes (i.e., peripheral attributes causing the bias), from a large number of bias-aligned samples, the bias attributes of which have strong correlation with the target variable. Using the disentangled representation, we synthesize bias-conflicting samples that contain the diverse intrinsic attributes of bias-aligned samples by swapping their latent features. By utilizing these diversified bias-conflicting features during the training, our approach achieves superior classification accuracy and debiasing results against the existing baselines on synthetic and real-world datasets.

研究动机与目标

• 动机：为了改善去偏和泛化，强调需要多样的偏置冲突样本。
• 提出一个用于内在属性和偏置属性的解耦潜在表示。
• 开发一种特征交换增强机制，以合成多样的偏置冲突样本。
• 引入一个调度策略，在解耦进展后再应用增强，以避免早期样本过于噪声。
• 在合成数据和真实偏置数据集上对比基线进行实证验证。

提出的方法

• 训练两个编码器，将图像表征分成 intrinsic (z_i) 与 bias (z_b) 潜在向量。
• 使用线性分类器分别从 z_i 和 z_b 预测标签，并采用联合损失强调偏置冲突样本。
• 计算相对难度权重 W(z) 以识别偏置冲突样本并驱动 intrinsic-attribute 学习 (L_dis)。
• 在样本之间交换潜在分量（z_swap = [z_i; swapped z_b]）以生成偏置冲突的增强特征 (L_swap)。
• 在部分解耦后再进行增强的时间调度，以避免早期阶段样本的噪声（算法工作流）。
• 在 Colored MNIST, Corrupted CIFAR-10, and Biased FFHQ (BFFHQ) 上对比基线进行评估。

实验结果

研究问题

• RQ1 多样的偏置冲突样本是否比训练集之外的样本还能提升去偏性能？
• RQ2 解耦的内在属性与偏置属性是否能使潜在空间增强在去偏中更有效？
• RQ3 特征增强调度对去偏性能有何影响？
• RQ4 所提出的方法相较于偏置显式与偏置无关的基线，在合成与真实偏置上表现如何？

主要发现

• 多样的偏置冲突样本显著提升跨数据集的去偏性能。
• 解耦的潜在表示使通过特征交换生成多样偏置冲突样本成为可能。
• 在部分解耦后进行的定时增强在所有实验中获得最佳无偏测试准确率。
• 所提方法在 Colored MNIST、Corrupted CIFAR-10、Biased FFHQ 上优于包括偏置显式与偏置无关的方法的基线。
• 在 Colored MNIST 上，即使在没有偏置类型预定义的情况下，该方法也达到比若干基线更高的测试准确率。