How to Not Measure Disentanglement
To evaluate disentangled representations several metrics have been proposed. However, theoretical guarantees for conventional metrics of disentanglement are missing. Moreover, conventional metrics do not have a consistent correlation with the outcomes of qualitative studies. In this paper we analyze metrics of disentanglement and their properties. We conclude that existing metrics of disentanglement were created to reflect different characteristics of disentanglement and do not satisfy two basic desirable properties: (1) assign a high score to representations that are disentangled according to the definition; and (2) assign a low score to representations that are entangled according to the definition. In addition, we propose a new metric of disentanglement and prove that it satisfies both of the properties.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementReinforcement LearningTransfer LearningZero-Shot LearningSimilar Papers 제목 키워드 기반
Defining and Measuring Disentanglement for non-Independent Factors of Variation
Representation learning is an approach that allows to discover and extract the factors of variation from the data. Intuitively, a representation is said to be disentangled if it separates the different factors of variati…
DisentanglementRepresentation LearningvalidMeasuring the Biases and Effectiveness of Content-Style Disentanglement
A recent spate of state-of-the-art semi- and un-supervised solutions disentangle and encode image "content" into a spatial tensor and image appearance or "style" into a vector, to achieve good performance in spatially eq…
DisentanglementImage-to-Image TranslationMeasuring the Effect of Causal Disentanglement on the Adversarial Robustness of Neural Network Models
Causal Neural Network models have shown high levels of robustness to adversarial attacks as well as an increased capacity for generalisation tasks such as few-shot learning and rare-context classification compared to tra…
Adversarial RobustnessBenchmarkingDisentanglementFew-Shot Learning+2Measuring Disentanglement: A Review of Metrics
Learning to disentangle and represent factors of variation in data is an important problem in AI. While many advances have been made to learn these representations, it is still unclear how to quantify disentanglement. Wh…
DisentanglementDisentanglement in Difference: Directly Learning Semantically Disentangled Representations by Maximizing Inter-Factor Differences
In this study, Disentanglement in Difference(DiD) is proposed to address the inherent inconsistency between the statistical independence of latent variables and the goal of semantic disentanglement in disentanglement rep…
DisentanglementRepresentation Learning