This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges. The core challenge is that people usually cannot obtain ground-truth explanations of the neural network. To this end, we design four metrics to evaluate explanation results without ground-truth explanations. Our metrics can be broadly applied to nine benchmark methods of interpreting neural networks, which provides new insights of explanation methods.
Explainable artificial intelligence (XAI) methods are currently evaluated with approaches mostly originated in interpretable machine learning (IML) research that focus on understanding models such as comparison against existing attribution approaches, sensitivity analyses, gold set of features, axioms, or through demonstration of images. There are problems with these methods such as that they do not indicate where current XAI approaches fail to guide investigations towards consistent progress of the field. They do not measure accuracy in support of accountable decisions, and it is practically …
University College Dublin（都柏林大学）；Insight Centre for Data Analytics（洞察数据分析中心）；VistaMilk SFI Research Centre（VistaMilk科学基金会爱尔兰研究中心）
Counterfactual explanations have emerged as a popular solution for the eXplainable AI (XAI) problem of elucidating the predictions of black-box deep-learning systems due to their psychological validity, flexibility across problem domains and proposed legal compliance. While over 100 counterfactual methods exist, claiming to generate plausible explanations akin to those preferred by people, few have actually been tested on users ($\sim7\%$). So, the psychological validity of these counterfactual algorithms for effective XAI for image data is not established. This issue is addressed here using a…
EPFL（洛桑联邦理工学院）；AXA（安盛）；Inria（法国国家信息与自动化研究所）；Sorbonne Université（索邦大学）；Polish Academy of Science（波兰科学院）
NLP Interpretability aims to increase trust in model predictions. This makes evaluating interpretability approaches a pressing issue. There are multiple datasets for evaluating NLP Interpretability, but their dependence on human provided ground truths raises questions about their unbiasedness. In this work, we take a different approach and formulate a specific classification task by diverting question-answering datasets. For this custom classification task, the interpretability ground-truth arises directly from the definition of the classification problem. We use this method to propose a bench…
In machine learning the best performance on a certain task is achieved by fully supervised methods when perfect ground truth labels are available. However, labels are often noisy, especially in remote sensing where manually curated public datasets are rare. We study the multi-modal cadaster map alignment problem for which available annotations are mis-aligned polygons, resulting in noisy supervision. We subsequently set up a multiple-rounds training scheme which corrects the ground truth annotations at each round to better train the model at the next round. We show that it is possible to reduc…
Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques are often not comprehensible to the end user. Lack of evaluation and selection criteria also makes it difficult for the end user to choose the most suitable technique. In this study, we combine logic-based argumentation with Interpretable Machine Learning, introducing a preliminary meta-explanation methodology that identifies the truthful parts of feature impo…
Explainable AI has attracted much research attention in recent years with feature attribution algorithms, which compute "feature importance" in predictions, becoming increasingly popular. However, there is little analysis of the validity of these algorithms as there is no "ground truth" in the existing datasets to validate their correctness. In this work, we develop a method to quantitatively evaluate the correctness of XAI algorithms by creating datasets with known explanation ground truth. To this end, we focus on the binary classification problems. String datasets are constructed using form…
Nonparametric approaches have shown promising results on reconstructing 3D human mesh from a single monocular image. Unlike previous approaches that use a parametric human model like skinned multi-person linear model (SMPL), and attempt to regress the model parameters, nonparametric approaches relax the heavy reliance on the parametric space. However, existing nonparametric methods require ground truth meshes as their regression target for each vertex, and obtaining ground truth mesh labels is very expensive. In this paper, we propose a novel approach to learn human mesh reconstruction without…
Accurately phenotyping plant wilting is important for understanding responses to environmental stress. Analysis of the shape of plants can potentially be used to accurately quantify the degree of wilting. Plant shape analysis can be enhanced by locating the stem, which serves as a consistent reference point during wilting. In this paper, we show that deep learning methods can accurately segment tomato plant stems. We also propose a control-point-based ground truth method that drastically reduces the resources needed to create a training dataset for a deep learning approach. Experimental result…
Hyperspectral unmixing (HU) is a very useful and increasingly popular preprocessing step for a wide range of hyperspectral applications. However, the HU research has been constrained a lot by three factors: (a) the number of hyperspectral images (especially the ones with ground truths) are very limited; (b) the ground truths of most hyperspectral images are not shared on the web, which may cause lots of unnecessary troubles for researchers to evaluate their algorithms; (c) the codes of most state-of-the-art methods are not shared, which may also delay the testing of new methods. Accordingly, t…
Benchmarking Time-localized Explanations for Audio Classification Models
UBAArgentina（UBA阿根廷）；CONICET-UBAArgentina（CONICET-UBA阿根廷）；Departamento de Computación, FCEyN（计算系）；Instituto de Investigación en Ciencias de la Computación (ICC)（计算机科学研究所）
Base-detail separation is a fundamental computer vision problem consisting of modeling a smooth base layer with the coarse structures, and a detail layer containing the texture-like structures. One of the challenges of estimating the base is to preserve sharp boundaries between objects or parts to avoid halo artifacts. Many methods have been proposed to address this problem, but there is no ground-truth dataset of real images for quantitative evaluation. We proposed a procedure to construct such a dataset, and provide two datasets: Pascal Base-Detail and Fashionista Base-Detail, containing 100…
University College London（伦敦大学学院）；University of Bath（巴斯大学）；Google（谷歌）
In this paper we present a dense ground truth dataset of nonrigidly deforming real-world scenes. Our dataset contains both long and short video sequences, and enables the quantitatively evaluation for RGB based tracking and registration methods. To construct ground truth for the RGB sequences, we simultaneously capture Near-Infrared (NIR) image sequences where dense markers - visible only in NIR - represent ground truth positions. This allows for comparison with automatically tracked RGB positions and the formation of error metrics. Most previous datasets containing nonrigidly deforming sequen…
Tsinghua University（清华大学）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Hong Kong University of Science and Technology（香港科技大学）；University College London（伦敦大学学院）
Multi-focus image fusion, a technique to generate an all-in-focus image from two or more partially-focused source images, can benefit many computer vision tasks. However, currently there is no large and realistic dataset to perform convincing evaluation and comparison of algorithms in multi-focus image fusion. Moreover, it is difficult to train a deep neural network for multi-focus image fusion without a suitable dataset. In this letter, we introduce a large and realistic multi-focus dataset called Real-MFF, which contains 710 pairs of source images with corresponding ground truth images. The …
Oxford Robotics Institute, Dept. Engineering Science, University of Oxford（牛津大学工程科学系牛津机器人研究所）；University of Oxford（牛津大学）
We describe the release of reference data towards a challenging long-term localisation and mapping benchmark based on the large-scale Oxford RobotCar Dataset. The release includes 72 traversals of a route through Oxford, UK, gathered in all illumination, weather and traffic conditions, and is representative of the conditions an autonomous vehicle would be expected to operate reliably in. Using post-processed raw GPS, IMU, and static GNSS base station recordings, we have produced a globally-consistent centimetre-accurate ground truth for the entire year-long duration of the dataset. Coupled wit…
Northwestern Polytechnical University（西北工业大学）；University of Calgary（卡尔加里大学）
Spectral unmixing is an important and challenging problem in hyperspectral data processing. This topic has been extensively studied and a variety of unmixing algorithms have been proposed in the literature. However, the lack of publicly available dataset with ground-truth makes it difficult to evaluate and compare the performance of unmixing algorithms in a quantitative and objective manner. Most of the existing works rely on the use of numerical synthetic data and an intuitive inspection of the results of real data. To alleviate this dilemma, in this study, we design several experimental scen…
Bots are frequently used in Github repositories to automate repetitive activities that are part of the distributed software development process. They communicate with human actors through comments. While detecting their presence is important for many reasons, no large and representative ground-truth dataset is available, nor are classification models to detect and validate bots on the basis of such a dataset. This paper proposes a ground-truth dataset, based on a manual analysis with high interrater agreement, of pull request and issue comments in 5,000 distinct Github accounts of which 527 ha…
Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how machine learning systems work and further enhance their trust towards systems. However, due to the diversified scenarios and subjective nature of explanations, we rarely have the ground truth for benchmark evaluation in IML on the quality of generated explanations. Having a sense of explanation quality not only matters for assessing system boundaries, but also he…
Be Careful When Evaluating Explanations Regarding Ground Truth
University of Warsaw（华沙大学）；Warsaw University of Technology（华沙理工大学）；University of Natural Resources and Life Sciences Vienna（维也纳自然资源与生命科学大学）；Medical University of Graz（格拉茨医科大学）
Adobe（奥多比公司）；University of Tennessee（田纳西大学）；Harvard Business School（哈佛商学院）；Harvard University（哈佛大学）；Broad Institute of MIT and Harvard（麻省理工学院和哈佛大学博德研究所）；Harvard Data Science Initiative（哈佛数据科学研究院）
As post hoc explanations are increasingly used to understand the behavior of graph neural networks (GNNs), it becomes crucial to evaluate the quality and reliability of GNN explanations. However, assessing the quality of GNN explanations is challenging as existing graph datasets have no or unreliable ground-truth explanations for a given task. Here, we introduce a synthetic graph data generator, ShapeGGen, which can generate a variety of benchmark datasets (e.g., varying graph sizes, degree distributions, homophilic vs. heterophilic graphs) accompanied by ground-truth explanations. Further, th…
Local explanations of learning-to-rank (LTR) models are thought to extract the most important features that contribute to the ranking predicted by the LTR model for a single data point. Evaluating the accuracy of such explanations is challenging since the ground truth feature importance scores are not available for most modern LTR models. In this work, we propose a systematic evaluation technique for explanations of LTR models. Instead of using black-box models, such as neural networks, we propose to focus on tree-based LTR models, from which we can extract the ground truth feature importance …
The effectiveness of binary analysis tools and techniques is often measured with respect to how well they map to a ground truth. We have found that not all ground truths are created equal. This paper challenges the binary analysis community to take a long look at the concept of ground truth, to ensure that we are in agreement with definition(s) of ground truth, so that we can be confident in the evaluation of tools and techniques. This becomes even more important as we move to trained machine learning models, which are only as useful as the validity of the ground truth in the training.
Universally valid ground truth is almost impossible to obtain or would come at a very high cost. For supervised learning without universally valid ground truth, a recommended approach is applying crowdsourcing: Gathering a large data set annotated by multiple individuals of varying possibly expertise levels and inferring the ground truth data to be used as labels to train the classifier. Nevertheless, due to the sensitivity of the problem at hand (e.g. mitosis detection in breast cancer histology images), the obtained data needs verification and proper assessment before being used for classifi…
Structural data well exists in Web applications, such as social networks in social media, citation networks in academic websites, and threads data in online forums. Due to the complex topology, it is difficult to process and make use of the rich information within such data. Graph Neural Networks (GNNs) have shown great advantages on learning representations for structural data. However, the non-transparency of the deep learning models makes it non-trivial to explain and interpret the predictions made by GNNs. Meanwhile, it is also a big challenge to evaluate the GNN explanations, since in man…
Exact ground truth invariant polynomial systems can be written for arbitrarily correlated binary classifiers. Their solutions give estimates for sample statistics that require knowledge of the ground truth of the correct labels in the sample. Of these polynomial systems, only a few have been solved in closed form. Here we discuss the exact solution for independent binary classifiers - resolving an outstanding problem that has been presented at this conference and others. Its practical applicability is hampered by its sole remaining assumption - the classifiers need to be independent in their s…
Classifiers commonly make use of pre-annotated datasets, wherein a model is evaluated by pre-defined metrics on a held-out test set typically made of human-annotated labels. Metrics used in these evaluations are tied to the availability of well-defined ground truth labels, and these metrics typically do not allow for inexact matches. These noisy ground truth labels and strict evaluation metrics may compromise the validity and realism of evaluation results. In the present work, we discuss these concerns and conduct a systematic posthoc verification experiment on the entity linking (EL) task. Un…
Regression analysis is a standard supervised machine learning method used to model an outcome variable in terms of a set of predictor variables. In most real-world applications we do not know the true value of the outcome variable being predicted outside the training data, i.e., the ground truth is unknown. It is hence not straightforward to directly observe when the estimate from a model potentially is wrong, due to phenomena such as overfitting and concept drift. In this paper we present an efficient framework for estimating the generalization error of regression functions, applicable to any…
Binary classification is widely used in ML production systems. Monitoring classifiers in a constrained event space is well known. However, real world production systems often lack the ground truth these methods require. Privacy concerns may also require that the ground truth needed to evaluate the classifiers cannot be made available. In these autonomous settings, non-parametric estimators of performance are an attractive solution. They do not require theoretical models about how the classifiers made errors in any given sample. They just estimate how many errors there are in a sample of an ind…
Jilin University（吉林大学）；Hefei University of Technology（合肥工业大学）
Partial Multi-label Learning (PML) aims to induce the multi-label predictor from datasets with noisy supervision, where each training instance is associated with several candidate labels but only partially valid. To address the noisy issue, the existing PML methods basically recover the ground-truth labels by leveraging the ground-truth confidence of the candidate label, \ie the likelihood of a candidate label being a ground-truth one. However, they neglect the information from non-candidate labels, which potentially contributes to the ground-truth label recovery. In this paper, we propose to …
Center for Machine Learning, Capital One（第一资本机器学习中心）；Tandon School of Engineering, New York University（纽约大学坦登工程学院）；Center for Data Science, New York University（纽约大学数据科学中心）；Card Machine Learning and Technology, Capital One（第一资本卡片机器学习与技术部）
In data science, there is a long history of using synthetic data for method development, feature selection and feature engineering. Our current interest in synthetic data comes from recent work in explainability. Today's datasets are typically larger and more complex - requiring less interpretable models. In the setting of \textit{post hoc} explainability, there is no ground truth for explanations. Inspired by recent work in explaining image classifiers that does provide ground truth, we propose a similar solution for tabular data. Using copulas, a concise specification of the desired statisti…
Seoul National University（首尔大学）；NAVER AI Lab（NAVER人工智能实验室）；NAVER CLOVA；Korea Advanced Institute of Science and Technology（韩国科学技术院）；Hanyang University（汉阳大学）
Despite recent explosion of interests in in-context learning, the underlying mechanism and the precise impact of the quality of demonstrations remain elusive. Intuitively, ground-truth labels should have as much impact in in-context learning (ICL) as supervised learning, but recent work reported that the input-label correspondence is significantly less important than previously thought. Intrigued by this counter-intuitive observation, we re-examine the importance of ground-truth labels in in-context learning. With the introduction of two novel metrics, namely Label-Correctness Sensitivity and …
Methods that detect user states such as emotions are useful for interactive systems. In this position paper, we argue for model-based approaches that are trained on user behaviour and self-reported user state as ground truths. In an application context, they record behaviour, extract relevant features, and use the models to predict user states. We describe how this approach can be implemented and discuss its benefits in comparison to solely self-reports in an application and to models of behaviour without the selfreport ground truths. Finally, we discuss shortcomings of this approach by consid…
Efficiently Transforming Neural Networks into Decision Trees: A Path to Ground Truth Explanations with RENTT
Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所）；Institute of Industrial Manufacturing and Management IFF, University of Stuttgart（工业制造与管理研究所，斯图加特大学）；Technical University Munich（慕尼黑技术大学）
Technion Israel Institute of Technology（以色列理工学院）；Bar-Ilan University（巴伊兰大学）
Training a deep neural network for classification constitutes a major problem in remote sensing due to the lack of adequate field data. Acquiring high-resolution ground truth (GT) by human interpretation is both cost-ineffective and inconsistent. We propose, instead, to utilize high-resolution, hyperspectral images for solving this problem, by unmixing these images to obtain reliable GT for training a deep network. Specifically, we simulate GT from high-resolution, hyperspectral FENIX images, and use it for training a convolutional neural network (CNN) for pixel-based classification. We show h…
The University of Melbourne（墨尔本大学）；RMIT University（皇家墨尔本理工大学）
It has been noticed that some external CVIs exhibit a preferential bias towards a larger or smaller number of clusters which is monotonic (directly or inversely) in the number of clusters in candidate partitions. This type of bias is caused by the functional form of the CVI model. For example, the popular Rand index (RI) exhibits a monotone increasing (NCinc) bias, while the Jaccard Index (JI) index suffers from a monotone decreasing (NCdec) bias. This type of bias has been previously recognized in the literature. In this work, we identify a new type of bias arising from the distribution of th…
Given a supervised/semi-supervised learning scenario where multiple annotators are available, we consider the problem of identification of adversarial or unreliable annotators.
Ghent University（根特大学）；VIB Inflammation Research Center（VIB炎症研究中心）
Distances between data points are widely used in machine learning applications. Yet, when corrupted by noise, these distances -- and thus the models based upon them -- may lose their usefulness in high dimensions. Indeed, the small marginal effects of the noise may then accumulate quickly, shifting empirical closest and furthest neighbors away from the ground truth. In this paper, we exactly characterize such effects in noisy high-dimensional data using an asymptotic probabilistic expression. Previously, it has been argued that neighborhood queries become meaningless and unstable when distance…
