This looks like that: deep learning for interpretable image recognition (2018-06-27T00:00:00.000000Z)

TL;DR

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.

Abstract

When we are faced with challenging image classification tasks, we often explain our reasoning by dissecting the image, and pointing out prototypical aspects of one class or another. The mounting evidence for each of the classes helps us make our final decision. In this work, we introduce a deep network architecture -- prototypical part network (ProtoPNet), that reasons in a similar way: the network dissects the image by finding prototypical parts, and combines evidence from the prototypes to make a final classification. The model thus reasons in a way that is qualitatively similar to the way ornithologists, physicians, and others would explain to people on how to solve challenging image classification tasks. The network uses only image-level labels for training without any annotations for parts of images. We demonstrate our method on the CUB-200-2011 dataset and the Stanford Cars dataset. Our experiments show that ProtoPNet can achieve comparable accuracy with its analogous non-interpretable counterpart, and when several ProtoPNets are combined into a larger network, it can achieve an accuracy that is on par with some of the best-performing deep models. Moreover, ProtoPNet provides a level of interpretability that is absent in other interpretable deep models.

Authors

C. Rudin

10 papers

A. Barnett

2 papers

Oscar Li

1 papers

TL;DR

Abstract

Authors

References72 items

Interpretable and Steerable Sequence Learning via Prototypes

Interpretable Basis Decomposition for Visual Explanation

Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning

Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction

Deep Learning for Case-based Reasoning through Prototypes: A Neural Network that Explains its Predictions

Interpretable Convolutional Neural Networks

Efficient implementation of a generalized convolutional neural networks based on weighted euclidean distance

Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition

Deep Learning to Improve Breast Cancer Detection on Screening Mammography

Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition

Generalizing the Convolution Operator in Convolutional Neural Networks

Methods for interpreting and understanding deep neural networks

SmoothGrad: removing noise by adding noise

Network Dissection: Quantifying Interpretability of Deep Visual Representations

Axiomatic Attribution for Deep Networks

Prototypal Analysis and Prototypal Regression

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

Densely Connected Convolutional Networks

SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition

Rationalizing Neural Predictions

Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

Fully Convolutional Attention Networks for Fine-Grained Recognition

Fully Convolutional Attention Localization Networks: Efficient Attention Localization for Fine-Grained Recognition

Pixel Recurrent Neural Networks

Part-Stacked CNN for Fine-Grained Visual Categorization

Learning Deep Features for Discriminative Localization

Deep Residual Learning for Image Recognition

Multiple Granularity Descriptors for Fine-Grained Categorization

ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering

Attention-Based Models for Speech Recognition

Understanding Neural Networks Through Deep Visualization

Fine-grained recognition without part annotations

Deep LAC: Deep localization, alignment and classification for fine-grained recognition

Spatial Transformer Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks

Bilinear CNN Models for Fine-Grained Visual Recognition

Fast R-CNN

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Adam: A Method for Stochastic Optimization

Striving for Simplicity: The All Convolutional Net

The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification

The application of two-level attention models in deep convolutional neural network for fine-grained image classification

From image-level to pixel-level labeling with Convolutional Networks

Very Deep Convolutional Networks for Large-Scale Image Recognition

Part-Based R-CNNs for Fine-Grained Category Detection

Bird Species Categorization Using Pose Normalized Deep Convolutional Nets

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

3D Object Representations for Fine-Grained Categorization

Visualizing and Understanding Convolutional Networks

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Selective Search for Object Recognition

Prototype selection for interpretable classification

The Caltech-UCSD Birds-200-2011 Dataset

ImageNet: A large-scale hierarchical image database

Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

Et al

Towards optimal bag-of-features for object categorization and semantic video retrieval

Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

Scalable Recognition with a Vocabulary Tree

Distance Metric Learning for Large Margin Nearest Neighbor Classification

Medical applications in case-based reasoning

A Bayesian hierarchical model for learning natural scene categories

Video Google: a text retrieval approach to object matching in videos

Classification Using Class Cover Catch Digraphs

Object recognition from local scale-invariant features

House sparrow identification. https://www.thespruce.com/ house-sparrow-identification-385983, 2016

A Practical Guide to Training Restricted Boltzmann Machines

Visualizing Higher-Layer Features of a Deep Network

Learning Multiple Layers of Features from Tiny Images

Gray's Anatomy

Field of Study

Venue Information

Name

Type