Optimising for Interpretability: Convolutional Dynamic Alignment Networks

  title={Optimising for Interpretability: Convolutional Dynamic Alignment Networks},
  author={Moritz D Boehle and Mario Fritz and Bernt Schiele},
  journal={IEEE transactions on pattern analysis and machine intelligence},
We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA Nets), which are performant classifiers with a high degree of inherent interpretability. Their core building blocks are Dynamic Alignment Units (DAUs), which are optimised to transform their inputs with dynamically computed weight vectors that align with task-relevant patterns. As a result, CoDA Nets model the classification prediction through a series of input-dependent linear… 



Striving for Simplicity: The All Convolutional Net

It is found that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks.

This looks like that: deep learning for interpretable image recognition

A deep network architecture -- prototypical part network (ProtoPNet), that reasons in a similar way to the way ornithologists, physicians, and others would explain to people on how to solve challenging image classification tasks, that provides a level of interpretability that is absent in other interpretable deep models.

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet

A high-performance DNN architecture on ImageNet whose decisions are considerably easier to explain is introduced, and behaves similar to state-of-the art deep neural networks such as VGG-16, ResNet-152 or DenseNet-169 in terms of feature sensitivity, error distribution and interactions between image parts.

Visualizing and Understanding Convolutional Networks

A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets), and establishes the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks.

Learning Important Features Through Propagating Activation Differences

DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of a neural network on a specific input by backpropagating the contributions of all neurons in the network to every feature of the input, is presented.

Towards Robust Interpretability with Self-Explaining Neural Networks

This work designs self-explaining models in stages, progressively generalizing linear classifiers to complex yet architecturally explicit models, and proposes three desiderata for explanations in general – explicitness, faithfulness, and stability.

Sanity Checks for Saliency Maps

It is shown that some existing saliency methods are independent both of the model and of the data generating process, and methods that fail the proposed tests are inadequate for tasks that are sensitive to either data or model.

Dynamic Filter Networks

The Dynamic Filter Network is introduced, where filters are generated dynamically conditioned on an input, and it is shown that this architecture is a powerful one, with increased flexibility thanks to its adaptive nature, yet without an excessive increase in the number of model parameters.

A Unified Approach to Interpreting Model Predictions

A unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), which unifies six existing methods and presents new methods that show improved computational performance and/or better consistency with human intuition than previous approaches.