Towards Deep Machine Reasoning: a Prototype-based Deep Neural Network with Decision Tree Inference
Plamen Angelov,Eduardo Soares +1 more
- pp 2092-2099
TLDR
A new approach specifically advantageous for imbalanced multi-class problems on well known hard benchmark datasets, which offers full explainability, does not require GPUs and can continue to learn from new data by adding new prototypes preserving the previous ones but not requiring full retraining.Abstract:
In this paper we introduce the DMR – a prototype-based method and network architecture for deep learning which is using a decision tree (DT)- based inference and synthetic data to balance the classes. It builds upon the recently introduced xDNN method addressing more complex multi-class problems, specifically when classes are highly imbalanced. DMR moves away from a direct decision based on all classes towards a layered DT of pair-wise class comparisons. In addition, it forces the prototypes to be balanced between classes regardless of possible class imbalances of the training data. It has two novel mechanisms, namely i) using a DT to determine the winning class label, and ii) balancing the classes by synthesizing data around the prototypes determined from the available training data. As a result, we improved significantly the performance of the resulting fully explainable DNN as evidenced on the well know benchmark problem Caltech-101. Furthermore, we also achieved high results in terms of accuracy for the well known Caltech-256 dataset, as well as surpassed the results of other approaches on Faces-1999 problem. In summary, we propose a new approach specifically advantageous for imbalanced multi-class problems on well known hard benchmark datasets. Moreover, DMR offers full explainability, does not require GPUs and can continue to learn from new data by adding new prototypes preserving the previous ones but not requiring full retraining.read more
Citations
More filters
Proceedings ArticleDOI
Neural Prototype Trees for Interpretable Fine-grained Image Recognition
TL;DR: ProtoTree as discussed by the authors combines prototype learning with decision trees, and thus results in a globally interpretable model by design, which can locally explain a single prediction by outlining a decision path through the tree.
Journal ArticleDOI
Privacy-preserving Case-based Explanations: Enabling visual interpretability by protecting privacy
TL;DR: It is concluded that most privacy-preserving methods are not sufficiently good to be applied to case-based explanations of image data, and formalizes the privacy protection of visual case- based explanations as a multi-objective problem to preserve privacy, intelligibility, and relevant explanatory evidence regarding a predictive task.
Journal ArticleDOI
Privacy-Preserving Case-Based Explanations: Enabling Visual Interpretability by Protecting Privacy
TL;DR: In this article , the authors identify the main limitations and challenges in the anonymization of case-based explanations of image data through a survey on casebased interpretability and image anonymization methods and empirically analyze the methods in regards to their capacity to remove personally identifiable information while preserving relevant semantic properties of the data.
Leveraging Interpretability: Concept-based Pedestrian Detection with Deep Neural Networks
TL;DR: In this paper, the authors propose a method for inherently interpretable and concept-based pedestrian detection (CPD), which explicitly structures the latent space with concept vectors that learn features for body parts as predefined concepts and predicts a body part segmentation based on distances of latent representations to concept vectors.
Proceedings ArticleDOI
Fuzzy Cognitive Maps for Interpretable Image-based Classification
TL;DR: In this paper , a novel interpretable classification scheme based on a Fuzzy Cognitive Map (FCM), named xFCM, is introduced, which is a directed graph with nodes representing semantic concepts of the real world, as these are illustrated within different images.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).