scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs

TL;DR: In this article, a post-hoc architecture-agnostic concept extractor (PACE) is proposed to automatically extract smaller sub-regions of the image called concepts relevant to the black-box prediction.
Abstract: Deep CNNs, though have achieved the state of the art performance in image classification tasks, remain a black-box to a human using them. There is a growing interest in explaining the working of these deep models to improve their trustworthiness. In this paper, we introduce a Posthoc Architecture-agnostic Concept Extractor (PACE) that automatically extracts smaller sub-regions of the image called concepts relevant to the black-box prediction. PACE tightly integrates the faithfulness of the explanatory framework to the black-box model. To the best of our knowledge, this is the first work that extracts class-specific discriminative concepts in a posthoc manner automatically. The PACE framework is used to generate explanations for two different CNN architectures trained for classifying the AWA2 and Imagenet- Birds datasets. Extensive human subject experiments are conducted to validate the human interpretability and consistency of the explanations extracted by PACE. The results from these experiments suggest that over 72% of the concepts extracted by PACE are human interpretable.
Citations
More filters
Journal ArticleDOI
TL;DR: This work studies concept-based explanations and put forward a new definition of concepts as lowdimensional subspaces of hidden feature layers, and empirically demonstrate the soundness of the proposed Sparse Subspace Clustering for Concept Discovery (SSCCD) method.
Abstract: Concepts are key building blocks of higher level human understanding. Explainable AI (XAI) methods have shown tremendous progress in recent years, however, local attribution methods do not allow to identify coherent model behavior across samples and therefore miss this essential component. In this work, we study concept-based explanations and put forward a new definition of concepts as low-dimensional subspaces of hidden feature layers. We novelly apply sparse subspace clustering to discover these concept subspaces. Moving forward, we derive insights from concept subspaces in terms of localized input (concept) maps, show how to quantify concept relevances and lastly, evaluate similarities and transferability between concepts. We empirically demonstrate the soundness of the proposed Sparse Subspace Clustering for Concept Discovery (SSCCD) method for a variety of different image classification tasks. This approach allows for deeper insights into the actual model behavior that would remain hidden from conventional input-level heatmaps.

4 citations

Journal ArticleDOI
01 Jul 2022-Sensors
TL;DR: It is demonstrated that ACE is a valid tool for gaining insights into the decision process of histopathological CNNs that can go beyond explanations from the control method and the complementary use with Guided Gradient-weighted Class Activation Mapping offers several benefits.
Abstract: Digital histopathology poses several challenges such as label noise, class imbalance, limited availability of labelled data, and several latent biases to deep learning, negatively influencing transparency, reproducibility, and classification performance. In particular, biases are well known to cause poor generalization. Proposed tools from explainable artificial intelligence (XAI), bias detection, and bias discovery suffer from technical challenges, complexity, unintuitive usage, inherent biases, or a semantic gap. A promising XAI method, not studied in the context of digital histopathology is automated concept-based explanation (ACE). It automatically extracts visual concepts from image data. Our objective is to evaluate ACE’s technical validity following design science principals and to compare it to Guided Gradient-weighted Class Activation Mapping (Grad-CAM), a conventional pixel-wise explanation method. To that extent, we created and studied five convolutional neural networks (CNNs) in four different skin cancer settings. Our results demonstrate that ACE is a valid tool for gaining insights into the decision process of histopathological CNNs that can go beyond explanations from the control method. ACE validly visualized a class sampling ratio bias, measurement bias, sampling bias, and class-correlated bias. Furthermore, the complementary use with Guided Grad-CAM offers several benefits. Finally, we propose practical solutions for several technical challenges. In contradiction to results from the literature, we noticed lower intuitiveness in some dermatopathology scenarios as compared to concept-based explanations on real-world images.

3 citations

Journal ArticleDOI
TL;DR: In this article , the authors propose Multi-dimensional Concept Discovery (MCD) which is an extension of previous approaches that fulfills a completeness relation on the level of concepts.
Abstract: The completeness axiom renders the explanation of a post-hoc XAI method only locally faithful to the model, i.e. for a single decision. For the trustworthy application of XAI, in particular for high-stake decisions, a more global model understanding is required. Recently, concept-based methods have been proposed, which are however not guaranteed to be bound to the actual model reasoning. To circumvent this problem, we propose Multi-dimensional Concept Discovery (MCD) as an extension of previous approaches that fulfills a completeness relation on the level of concepts. Our method starts from general linear subspaces as concepts and does neither require reinforcing concept interpretability nor re-training of model parts. We propose sparse subspace clustering to discover improved concepts and fully leverage the potential of multi-dimensional subspaces. MCD offers two complementary analysis tools for concepts in input space: (1) concept activation maps, that show where a concept is expressed within a sample, allowing for concept characterization through prototypical samples, and (2) concept relevance heatmaps, that decompose the model decision into concept contributions. Both tools together enable a detailed understanding of the model reasoning, which is guaranteed to relate to the model via a completeness relation. This paves the way towards more trustworthy concept-based XAI. We empirically demonstrate the superiority of MCD against more constrained concept definitions.

2 citations

Proceedings ArticleDOI
01 Jan 2023
TL;DR: In this article , the authors propose a unified evaluation protocol for the quantitative evaluation of interpretation methods, which is achieved by enhancing existing interpretation methods to be capable of generating visual explanations and then linking these explanations with a semantic label.
Abstract: With the continuous development of Convolutional Neural Networks (CNNs), there is an increasing requirement towards the understanding of the representations they internally encode. The task of studying such encoded representations is referred to as model interpretation. Efforts along this direction, despite being proved efficient, stand with two weaknesses. First, there is low semanticity on the feedback they provide which leads toward subjective visualizations. Second, there is no unified protocol for the quantitative evaluation of interpretation methods which makes the comparison between current and future methods complex.To address these issues, we propose a unified evaluation protocol for the quantitative evaluation of interpretation methods. This is achieved by enhancing existing interpretation methods to be capable of generating visual explanations and then linking these explanations with a semantic label. To achieve this, we introduce the Weighted Average Intersection-over-Union (WAIoU) metric to estimate the coverage rate between explanation heatmaps and semantic annotations. This is complemented with an analysis of several binarization techniques for heatmaps, necessary when measuring coverage. Experiments considering several interpretation methods covering different CNN architectures pre-trained on multiple datasets show the effectiveness of the proposed protocol.

1 citations

Journal ArticleDOI
TL;DR: In this article , the authors propose a framework for the study of interpretation methods designed for CNN models trained from visual data and define a set of six specific factors that can be used to characterize interpretation methods.
Abstract: With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as model interpretation. While the task of model explanation, justifying the predictions of such models, has been studied extensively; the task of model interpretation has received less attention. The aim of this paper is to propose a framework for the study of interpretation methods designed for CNN models trained from visual data. More specifically, we first specify the difference between the interpretation and explanation tasks which are often considered the same in the literature. Then, we define a set of six specific factors that can be used to characterize interpretation methods. Third, based on the previous factors, we propose a framework for the positioning of interpretation methods. Our framework highlights that just a very small amount of the suggested factors, and combinations thereof, have been actually studied. Consequently, leaving significant areas unexplored. Following the proposed framework, we discuss existing interpretation methods and give some attention to the evaluation protocols followed to validate them. Finally, the paper highlights capabilities of the methods in producing feedback for enabling interpretation and proposes possible research problems arising from the framework.
References
More filters
Proceedings ArticleDOI
27 Jun 2016
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.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

123,388 citations

Proceedings Article
01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Abstract: We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.

111,197 citations

Proceedings Article
01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) 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. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

49,914 citations

Journal ArticleDOI
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Abstract: The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the 5 years of the challenge, and propose future directions and improvements.

30,811 citations

Proceedings ArticleDOI
13 Aug 2016
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
Abstract: Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally varound the prediction. We also propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). We show the utility of explanations via novel experiments, both simulated and with human subjects, on various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and identifying why a classifier should not be trusted.

11,104 citations