Disentangled representations: towards interpretation of sex determination from hip bone

• URL: http://arxiv.org/abs/2112.09414v1
• Date: Fri, 17 Dec 2021 10:07:05 GMT
• Title: Disentangled representations: towards interpretation of sex determination from hip bone
• Authors: Kaifeng Zou, Sylvain Faisan, Fabrice Heitz, Marie Epain, Pierre Croisille, Laurent Fanton, S\'ebastien Valette
• Abstract summary: saliency maps have become a popular method to make neural networks interpretable. We propose a new paradigm for better interpretability. We illustrate the relevance of this approach in the context of automatic sex determination from hip bones in forensic medicine.
• Score: 1.0775419935941009
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: By highlighting the regions of the input image that contribute the most to the decision, saliency maps have become a popular method to make neural networks interpretable. In medical imaging, they are particularly well-suited to explain neural networks in the context of abnormality localization. However, from our experiments, they are less suited to classification problems where the features that allow to distinguish between the different classes are spatially correlated, scattered and definitely non-trivial. In this paper we thus propose a new paradigm for better interpretability. To this end we provide the user with relevant and easily interpretable information so that he can form his own opinion. We use Disentangled Variational Auto-Encoders which latent representation is divided into two components: the non-interpretable part and the disentangled part. The latter accounts for the categorical variables explicitly representing the different classes of interest. In addition to providing the class of a given input sample, such a model offers the possibility to transform the sample from a given class to a sample of another class, by modifying the value of the categorical variables in the latent representation. This paves the way to easier interpretation of class differences. We illustrate the relevance of this approach in the context of automatic sex determination from hip bones in forensic medicine. The features encoded by the model, that distinguish the different classes were found to be consistent with expert knowledge.

Related papers

• Finding Interpretable Class-Specific Patterns through Efficient Neural Search [43.454121220860564]
  We propose a novel, inherently interpretable binary neural network architecture DNAPS that extracts differential patterns from data. DiffNaps is scalable to hundreds of thousands of features and robust to noise. We show on synthetic and real world data, including three biological applications, that, unlike its competitors, DiffNaps consistently yields accurate, succinct, and interpretable class descriptions.
  arXiv  Detail & Related papers  (2023-12-07T14:09:18Z)
• Variational Classification [51.2541371924591]
  We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency. We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
  arXiv  Detail & Related papers  (2023-05-17T17:47:19Z)
• A Test Statistic Estimation-based Approach for Establishing Self-interpretable CNN-based Binary Classifiers [7.424003880270276]
  Post-hoc interpretability methods have the limitation that they can produce plausible but different interpretations. The proposed method is self-interpretable, quantitative. Unlike the traditional post-hoc interpretability methods, the proposed method is self-interpretable, quantitative.
  arXiv  Detail & Related papers  (2023-03-13T05:51:35Z)
• Neural Representations Reveal Distinct Modes of Class Fitting in Residual Convolutional Networks [5.1271832547387115]
  We leverage probabilistic models of neural representations to investigate how residual networks fit classes. We find that classes in the investigated models are not fitted in an uniform way. We show that the uncovered structure in neural representations correlate with robustness of training examples and adversarial memorization.
  arXiv  Detail & Related papers  (2022-12-01T18:55:58Z)
• Equivariance with Learned Canonicalization Functions [77.32483958400282]
  We show that learning a small neural network to perform canonicalization is better than using predefineds. Our experiments show that learning the canonicalization function is competitive with existing techniques for learning equivariant functions across many tasks.
  arXiv  Detail & Related papers  (2022-11-11T21:58:15Z)
• Invariant Representations with Stochastically Quantized Neural Networks [5.7923858184309385]
  We propose a methodology for direct computation of the mutual information between a neural layer and a sensitive attribute. We show that this method compares favorably with the state of the art in fair representation learning.
  arXiv  Detail & Related papers  (2022-08-04T13:36:06Z)
• Fair Interpretable Learning via Correction Vectors [68.29997072804537]
  We propose a new framework for fair representation learning centered around the learning of "correction vectors" The corrections are then simply summed up to the original features, and can therefore be analyzed as an explicit penalty or bonus to each feature. We show experimentally that a fair representation learning problem constrained in such a way does not impact performance.
  arXiv  Detail & Related papers  (2022-01-17T10:59:33Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• Discriminative Attribution from Counterfactuals [64.94009515033984]
  We present a method for neural network interpretability by combining feature attribution with counterfactual explanations. We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
  arXiv  Detail & Related papers  (2021-09-28T00:53:34Z)
• Deducing neighborhoods of classes from a fitted model [68.8204255655161]
  In this article a new kind of interpretable machine learning method is presented. It can help to understand the partitioning of the feature space into predicted classes in a classification model using quantile shifts. Basically, real data points (or specific points of interest) are used and the changes of the prediction after slightly raising or decreasing specific features are observed.
  arXiv  Detail & Related papers  (2020-09-11T16:35:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.