CENDRe: Concept Extraction with Natural Domain Representations

• URL: http://arxiv.org/abs/2607.29621v1
• Date: Fri, 31 Jul 2026 16:56:27 GMT
• Title: CENDRe: Concept Extraction with Natural Domain Representations
• Abstract summary: We propose CENDRe, a concept extraction method for convolutional neural networks (CNNs)<n>CENDRe discovers concepts by clustering per-timestep latent representations in two stages, where silhouette-guided aggregation selects the number of concepts automatically.<n>It localizes each concept through gradients of a presence score that contrasts the latent representations with their prototypes, producing masks that concentrate on the regions driving the concept.<n>On real bearing-fault data, CENDRe extracts the frequency bands driving the model's predictions, located in regions commonly inspected for fault diagnosis.
• Score: 10.61206107163781
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Convolutional neural networks (CNNs) are widely used for time-series classification, but their deployment in critical domains requires understanding the temporal and spectral patterns that drive their predictions. Concept extraction (CE) methods identify such patterns by analyzing representations within the models' latent space. However, existing time-series CE methods have three limitations: they operate only in the time domain and overlook frequency features, predefine the number of concepts, and produce localizations misaligned with the regions the model uses. We address these limitations by proposing CENDRe, a concept extraction method for CNNs. It first discovers concepts by clustering per-timestep latent representations in two stages, where silhouette-guided aggregation selects the number of concepts automatically. Then, it localizes each concept through gradients of a presence score that contrasts the latent representations with their prototypes, producing masks that concentrate on the regions driving the concept. These gradients, propagated through a differentiable invertible mapping of the input such as a Fourier transform, yield localizations for the same concepts in the frequency domain. Finally, each concept receives a relevance score that quantifies its contribution to each class. On synthetic benchmarks, CENDRe achieves representation correctness comparable to state-of-the-art CE methods and significantly higher importance correctness. On real bearing-fault data, CENDRe extracts the frequency bands driving the model's predictions, located in regions commonly inspected for fault diagnosis, producing evidence to assess the model that time-domain CE methods cannot.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models [81.26524429852992]
  PuRF is a novel PuRiFication-driven cache-based method for multi-label test-time adaptation of vision-language models.<n>We show PuRF consistently outperforms state-of-the-art methods, achieving a notable 4.05% mAP improvement on ViT-B/32 across five datasets.
  arXiv  Detail & Related papers  (2026-08-26T11:36:11Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Concept Extraction for Time Series with ECLAD-ts [5.467140383171385]
  CNNs for time series classification (TSC) are being increasingly used in applications ranging from quality prediction to medical diagnosis.<n>CNNs are prone to learning shortcuts and biases, compromising their robustness and alignment with human expectations.<n>To assess whether such mechanisms are being used and the associated risk, it is essential to provide model explanations that reflect the inner workings of the model.
  arXiv  Detail & Related papers  (2025-04-07T12:49:20Z)
• Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models [8.96655290787267]
  We present a unified framework for transforming any vision neural network into a spatially and conceptually interpretable model.<n>We name this method "Spatially-Aware and Label-Free Concept Bottleneck Model" (SALF-CBM)
  arXiv  Detail & Related papers  (2025-02-27T14:27:55Z)
• TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction [14.396966854171273]
  We consider the problem of single-source domain generalization.<n>Existing methods typically rely on extensive augmentations to synthetically cover diverse domains during training.<n>We propose an approach that compels models to leverage such local concepts during prediction.
  arXiv  Detail & Related papers  (2024-11-25T08:46:37Z)
• Exploiting Diffusion Prior for Generalizable Dense Prediction [85.4563592053464]
  Recent advanced Text-to-Image (T2I) diffusion models are sometimes too imaginative for existing off-the-shelf dense predictors to estimate. We introduce DMP, a pipeline utilizing pre-trained T2I models as a prior for dense prediction tasks. Despite limited-domain training data, the approach yields faithful estimations for arbitrary images, surpassing existing state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2023-11-30T18:59:44Z)
• Reconstructing Spatiotemporal Data with C-VAEs [49.1574468325115]
  Conditional continuous representation of moving regions is commonly used. In this work, we explore the capabilities of Conditional Varitemporal Autoencoder (C-VAE) models to generate realistic representations of regions' evolution.
  arXiv  Detail & Related papers  (2023-07-12T15:34:10Z)
• Point-Based Value Iteration for POMDPs with Neural Perception Mechanisms [31.51588071503617]
  We introduce neuro-symbolic partially observable Markov decision processes (NS-POMDPs) We propose a novel piecewise linear and convex representation (P-PWLC) in terms of polyhedra covering the state space and value vectors. We show the practical applicability of our approach on two case studies that employ (trained) ReLU neural networks as perception functions.
  arXiv  Detail & Related papers  (2023-06-30T13:26:08Z)
• 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)
• Modeling Temporal Concept Receptive Field Dynamically for Untrimmed Video Analysis [105.06166692486674]
  We study temporal concept receptive field of concept-based event representation. We introduce temporal dynamic convolution (TDC) to give stronger flexibility to concept-based event analytics. Different coefficients can generate appropriate and accurate temporal concept receptive field size according to input videos.
  arXiv  Detail & Related papers  (2021-11-23T04:59:48Z)
• Closed-Form Factorization of Latent Semantics in GANs [65.42778970898534]
  A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. We propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights.
  arXiv  Detail & Related papers  (2020-07-13T18:05:36Z)

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.