Few-class Fidelity: Evaluating Explanations of Real-conditions CNN classifiers with Optimized Perturbations

• URL: http://arxiv.org/abs/2606.28391v1
• Date: Tue, 23 Jun 2026 17:26:47 GMT
• Title: Few-class Fidelity: Evaluating Explanations of Real-conditions CNN classifiers with Optimized Perturbations
• Abstract summary: This paper proposes a variation of Fidelity-based XAI metrics, with a focus on real-conditions applications.<n>It highlights the intricate correlation between domain, data curation, and XAI solution choices in order to validate training of a new CNN model.
• Score: 1.6682715542079578
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The wide use of Convolutional Neural Networks (CNN) in numerous domains and real-world classification applications is justified by their high precision and automation speed, helping users concentrate on higher-expertise tasks. To better understand the models and avoid bias during deployment, eXplainable Artificial Intelligence (XAI) techniques can be used after training. But as the list of XAI solutions expand, comparisons between them diverge, and consensus over their evaluation cannot be reached. This paper proposes a variation of Fidelity-based XAI metrics, with a focus on real-conditions applications, where the number of classes is often low. The approach generates in-distribution, uncertainty-provoking perturbations, to ensure proper measurement of the XAI methods faithfulness. As demonstration of the evaluation framework usefulness, it is compared with human-centric object localization and segmentation metrics. Once applied to both medical and natural imaging applications, it highlights the intricate correlation between domain, data curation, and XAI solution choices in order to validate training of a new CNN model.

Related papers

• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• Soft-CAM: Making black box models self-explainable for high-stakes decisions [6.635611625764804]
  Convolutional neural networks (CNNs) are widely used for high-stakes applications like medicine, often surpassing human performance.<n>Most explanation methods rely on post-hoc attribution, approximating the decision-making process of already trained black-box models.<n>We introduce SoftCAM, a straightforward yet effective approach that makes standard CNN architectures inherently interpretable.
  arXiv  Detail & Related papers  (2025-05-23T11:15:21Z)
• Continuous Visual Autoregressive Generation via Score Maximization [69.67438563485887]
  We introduce a Continuous VAR framework that enables direct visual autoregressive generation without vector quantization.<n>Within this framework, all we need is to select a strictly proper score and set it as the training objective to optimize.
  arXiv  Detail & Related papers  (2025-05-12T17:58:14Z)
• CASC-AI: Consensus-aware Self-corrective Learning for Noise Cell Segmentation [8.50335568530725]
  Multi-class cell segmentation in high-resolution gigapixel whole slide images is crucial for various clinical applications.<n>Recent efforts have democratized this process by involving lay annotators without medical expertise.<n>We propose a consensus-aware self-corrective AI agent that leverages the Consensus Matrix to guide its learning process.
  arXiv  Detail & Related papers  (2025-02-11T06:58:50Z)
• Multi-Modal Prompt Learning on Blind Image Quality Assessment [65.0676908930946]
  Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. This paper introduces an innovative multi-modal prompt-based methodology for IQA.
  arXiv  Detail & Related papers  (2024-04-23T11:45:32Z)
• DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models [21.85879890198875]
  Decentralized Iterative Merging-And-Training (DIMAT) is a novel decentralized deep learning algorithm. We show that DIMAT attains faster and higher initial gain in accuracy with independent and identically distributed (IID) and non-IID data, incurring lower communication overhead. This DIMAT paradigm presents a new opportunity for the future decentralized learning, enhancing its adaptability to real-world with sparse lightweight communication computation.
  arXiv  Detail & Related papers  (2024-04-11T18:34:29Z)
• Activate and Reject: Towards Safe Domain Generalization under Category Shift [71.95548187205736]
  We study a practical problem of Domain Generalization under Category Shift (DGCS) It aims to simultaneously detect unknown-class samples and classify known-class samples in the target domains. Compared to prior DG works, we face two new challenges: 1) how to learn the concept of unknown'' during training with only source known-class samples, and 2) how to adapt the source-trained model to unseen environments.
  arXiv  Detail & Related papers  (2023-10-07T07:53:12Z)
• Extending CAM-based XAI methods for Remote Sensing Imagery Segmentation [7.735470452949379]
  We introduce a new XAI evaluation methodology and metric based on "Entropy" to measure the model uncertainty. We show that using Entropy to monitor the model uncertainty in segmenting the pixels within the target class is more suitable.
  arXiv  Detail & Related papers  (2023-10-03T07:01:23Z)
• Robust-by-Design Classification via Unitary-Gradient Neural Networks [66.17379946402859]
  The use of neural networks in safety-critical systems requires safe and robust models, due to the existence of adversarial attacks. Knowing the minimal adversarial perturbation of any input x, or, equivalently, the distance of x from the classification boundary, allows evaluating the classification robustness, providing certifiable predictions. A novel network architecture named Unitary-Gradient Neural Network is presented. Experimental results show that the proposed architecture approximates a signed distance, hence allowing an online certifiable classification of x at the cost of a single inference.
  arXiv  Detail & Related papers  (2022-09-09T13:34:51Z)
• Domain Adaptation Principal Component Analysis: base linear method for learning with out-of-distribution data [55.41644538483948]
  Domain adaptation is a popular paradigm in modern machine learning. We present a method called Domain Adaptation Principal Component Analysis (DAPCA) DAPCA finds a linear reduced data representation useful for solving the domain adaptation task.
  arXiv  Detail & Related papers  (2022-08-28T21:10:56Z)
• Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset [0.05156484100374058]
  We provide a framework to generate attribution benchmark datasets for regression problems in the geosciences. We train a fully-connected network to learn the underlying function that was used for simulation. We compare estimated attribution heatmaps from different XAI methods to the ground truth in order to identify examples where specific XAI methods perform well or poorly.
  arXiv  Detail & Related papers  (2021-03-18T03:39:17Z)

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.