Data-Adaptive Discriminative Feature Localization with Statistically Guaranteed Interpretation

• URL: http://arxiv.org/abs/2211.10061v1
• Date: Fri, 18 Nov 2022 07:20:00 GMT
• Title: Data-Adaptive Discriminative Feature Localization with Statistically Guaranteed Interpretation
• Authors: Ben Dai, Xiaotong Shen, Lin Yee Chen, Chunlin Li, Wei Pan
• Abstract summary: We use two real datasets, the MNIST handwritten digits and MIT-BIH Electrocardiogram signals, to motivate key characteristics of discriminative features. We develop a localization framework based on adversarial attacks to effectively localize discriminative features. In the first, the compact image regions localized by the proposed method are visually appealing. In the second, the identified ECG features are biologically plausible and consistent with cardiac electrophysiological principles.
• Score: 10.122986238546492
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In explainable artificial intelligence, discriminative feature localization is critical to reveal a blackbox model's decision-making process from raw data to prediction. In this article, we use two real datasets, the MNIST handwritten digits and MIT-BIH Electrocardiogram (ECG) signals, to motivate key characteristics of discriminative features, namely adaptiveness, predictive importance and effectiveness. Then, we develop a localization framework based on adversarial attacks to effectively localize discriminative features. In contrast to existing heuristic methods, we also provide a statistically guaranteed interpretability of the localized features by measuring a generalized partial $R^2$. We apply the proposed method to the MNIST dataset and the MIT-BIH dataset with a convolutional auto-encoder. In the first, the compact image regions localized by the proposed method are visually appealing. Similarly, in the second, the identified ECG features are biologically plausible and consistent with cardiac electrophysiological principles while locating subtle anomalies in a QRS complex that may not be discernible by the naked eye. Overall, the proposed method compares favorably with state-of-the-art competitors. Accompanying this paper is a Python library dnn-locate (https://dnn-locate.readthedocs.io/en/latest/) that implements the proposed approach.

Related papers

• CLIP-Clique: Graph-based Correspondence Matching Augmented by Vision Language Models for Object-based Global Localization [0.0]
  One of the most promising approaches for localization on object maps is to use semantic graph matching. To address the former issue, we augment the correspondence matching using Vision Language Models. In addition, inliers are estimated deterministically using a graph-theoretic approach.
  arXiv  Detail & Related papers  (2024-10-04T00:23:20Z)
• Refining Tuberculosis Detection in CXR Imaging: Addressing Bias in Deep Neural Networks via Interpretability [1.9936075659851882]
  We argue that the reliability of deep learning models is limited, even if they can be shown to obtain perfect classification accuracy on the test data. We show that pre-training a deep neural network on a large-scale proxy task, as well as using mixed objective optimization network (MOON), can improve the alignment of decision foundations between models and experts.
  arXiv  Detail & Related papers  (2024-07-19T06:41:31Z)
• Physics Inspired Hybrid Attention for SAR Target Recognition [61.01086031364307]
  We propose a physics inspired hybrid attention (PIHA) mechanism and the once-for-all (OFA) evaluation protocol to address the issues. PIHA leverages the high-level semantics of physical information to activate and guide the feature group aware of local semantics of target. Our method outperforms other state-of-the-art approaches in 12 test scenarios with same ASC parameters.
  arXiv  Detail & Related papers  (2023-09-27T14:39:41Z)
• Adaptive Face Recognition Using Adversarial Information Network [57.29464116557734]
  Face recognition models often degenerate when training data are different from testing data. We propose a novel adversarial information network (AIN) to address it.
  arXiv  Detail & Related papers  (2023-05-23T02:14:11Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Polar Encoding: A Simple Baseline Approach for Classification with Missing Values [1.7205106391379026]
  polar encoding is a representation of $[0,1]$-valued attributes with missing values. It does not require imputation, ensures that missing values are equidistant from non-missing values, and lets decision tree algorithms choose how to split missing values. We show that, in terms of the resulting classification performance, polar encoding performs better than the state-of-the-art strategies "multiple imputation by chained equations" and "multiple imputation with denoising autoencoders"
  arXiv  Detail & Related papers  (2022-10-04T20:56:24Z)
• Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition [54.23513799338309]
  We present an Adaptive Local-Component-aware Graph Convolutional Network for skeleton-based action recognition. Our method provides a stronger representation than the global embedding and helps our model reach state-of-the-art.
  arXiv  Detail & Related papers  (2022-09-21T02:33:07Z)
• ECLAD: Extracting Concepts with Local Aggregated Descriptors [6.470466745237234]
  We propose a novel method for automatic concept extraction and localization based on representations obtained through pixel-wise aggregations of CNN activation maps. We introduce a process for the validation of concept-extraction techniques based on synthetic datasets with pixel-wise annotations of their main components.
  arXiv  Detail & Related papers  (2022-06-09T14:25:23Z)
• Optimizing Speech Emotion Recognition using Manta-Ray Based Feature Selection [1.4502611532302039]
  We show that concatenation of features, extracted by using different existing feature extraction methods can boost the classification accuracy. We also perform a novel application of Manta Ray optimization in speech emotion recognition tasks that resulted in a state-of-the-art result.
  arXiv  Detail & Related papers  (2020-09-18T16:09:34Z)
• UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders [81.5490760424213]
  We propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Inspired by the saliency data labeling process, we propose probabilistic RGB-D saliency detection network.
  arXiv  Detail & Related papers  (2020-04-13T04:12:59Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.