GCPV: Guided Concept Projection Vectors for the Explainable Inspection of CNN Feature Spaces

• URL: http://arxiv.org/abs/2311.14435v1
• Date: Fri, 24 Nov 2023 12:22:00 GMT
• Title: GCPV: Guided Concept Projection Vectors for the Explainable Inspection of CNN Feature Spaces
• Authors: Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade
• Abstract summary: We introduce the local-to-global Guided Concept Projection Vectors (GCPV) approach. GCPV generates local concept vectors that each precisely reconstruct a concept segmentation label. It then generalizes these to global concept and even sub-concept vectors by means of hiearchical clustering.
• Score: 1.0923877073891446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: For debugging and verification of computer vision convolutional deep neural networks (CNNs) human inspection of the learned latent representations is imperative. Therefore, state-of-the-art eXplainable Artificial Intelligence (XAI) methods globally associate given natural language semantic concepts with representing vectors or regions in the CNN latent space supporting manual inspection. Yet, this approach comes with two major disadvantages: They are locally inaccurate when reconstructing a concept label and discard information about the distribution of concept instance representations. The latter, though, is of particular interest for debugging, like finding and understanding outliers, learned notions of sub-concepts, and concept confusion. Furthermore, current single-layer approaches neglect that information about a concept may be spread over the CNN depth. To overcome these shortcomings, we introduce the local-to-global Guided Concept Projection Vectors (GCPV) approach: It (1) generates local concept vectors that each precisely reconstruct a concept segmentation label, and then (2) generalizes these to global concept and even sub-concept vectors by means of hiearchical clustering. Our experiments on object detectors demonstrate improved performance compared to the state-of-the-art, the benefit of multi-layer concept vectors, and robustness against low-quality concept segmentation labels. Finally, we demonstrate that GCPVs can be applied to find root causes for confusion of concepts like bus and truck, and reveal interesting concept-level outliers. Thus, GCPVs pose a promising step towards interpretable model debugging and informed data improvement.

Related papers

• Concept-Guided Interpretability via Neural Chunking [54.73787666584143]
  We show that neural networks exhibit patterns in their raw population activity that mirror regularities in the training data.<n>We propose three methods to extract these emerging entities, complementing each other based on label availability and dimensionality.<n>Our work points to a new direction for interpretability, one that harnesses both cognitive principles and the structure of naturalistic data.
  arXiv  Detail & Related papers  (2025-05-16T13:49:43Z)
• Escaping Plato's Cave: Robust Conceptual Reasoning through Interpretable 3D Neural Object Volumes [65.63534641857476]
  We introduce CAVE - Concept Aware Volumes for Explanations - a new direction that unifies interpretability and robustness in image classification. We design an inherently-interpretable and robust classifier by extending existing 3D-aware classifiers with concepts extracted from their volumetric representations for classification. In an array of quantitative metrics for interpretability, we compare against different concept-based approaches across the explainable AI literature and show that CAVE discovers well-grounded concepts that are used consistently across images, while achieving superior robustness.
  arXiv  Detail & Related papers  (2025-03-17T17:55:15Z)
• Zero-shot Concept Bottleneck Models [17.70684428339905]
  Concept bottleneck models (CBMs) are inherently interpretable and intervenable neural network models. We present textitzero-shot concept bottleneck models (Z-CBMs), which predict concepts and labels in a fully zero-shot manner without training neural networks.
  arXiv  Detail & Related papers  (2025-02-13T07:11:07Z)
• OmniPrism: Learning Disentangled Visual Concept for Image Generation [57.21097864811521]
  Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. We propose OmniPrism, a visual concept disentangling approach for creative image generation. Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts.
  arXiv  Detail & Related papers  (2024-12-16T18:59:52Z)
• Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification [3.9626211140865464]
  Convolutional Neural Networks (CNNs) have seen significant performance improvements in recent years. However, due to their size and complexity, they function as black-boxes, leading to transparency concerns. This paper introduces a novel post-hoc explainability framework, Visual-TCAV, which aims to bridge the gap between these methods.
  arXiv  Detail & Related papers  (2024-11-08T16:52:52Z)
• Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery [52.498055901649025]
  Concept Bottleneck Models (CBMs) have been proposed to address the 'black-box' problem of deep neural networks. We propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model.
  arXiv  Detail & Related papers  (2024-07-19T17:50:11Z)
• Locally Testing Model Detections for Semantic Global Concepts [3.112979958793927]
  We propose a framework for linking global concept encodings to the local processing of single network inputs. Our approach has the advantage of fully covering the model-internal encoding of the semantic concept. The results show major differences in the local perception and usage of individual global concept encodings.
  arXiv  Detail & Related papers  (2024-05-27T12:52:45Z)
• Concept Activation Regions: A Generalized Framework For Concept-Based Explanations [95.94432031144716]
  Existing methods assume that the examples illustrating a concept are mapped in a fixed direction of the deep neural network's latent space. In this work, we propose allowing concept examples to be scattered across different clusters in the DNN's latent space. This concept activation region (CAR) formalism yields global concept-based explanations and local concept-based feature importance.
  arXiv  Detail & Related papers  (2022-09-22T17:59:03Z)
• Concept Gradient: Concept-based Interpretation Without Linear Assumption [77.96338722483226]
  Concept Activation Vector (CAV) relies on learning a linear relation between some latent representation of a given model and concepts. We proposed Concept Gradient (CG), extending concept-based interpretation beyond linear concept functions. We demonstrated CG outperforms CAV in both toy examples and real world datasets.
  arXiv  Detail & Related papers  (2022-08-31T17:06:46Z)
• Sparse Subspace Clustering for Concept Discovery (SSCCD) [1.7319807100654885]
  Concepts are key building blocks of higher level human understanding. Local attribution methods do not allow to identify coherent model behavior across samples. We put forward a new definition of concepts as low-dimensional subspaces of hidden feature layers.
  arXiv  Detail & Related papers  (2022-03-11T16:15:48Z)
• Human-Centered Concept Explanations for Neural Networks [47.71169918421306]
  We introduce concept explanations including the class of Concept Activation Vectors (CAV) We then discuss approaches to automatically extract concepts, and approaches to address some of their caveats. Finally, we discuss some case studies that showcase the utility of such concept-based explanations in synthetic settings and real world applications.
  arXiv  Detail & Related papers  (2022-02-25T01:27:31Z)
• Unsupervised Learning of Compositional Energy Concepts [70.11673173291426]
  We propose COMET, which discovers and represents concepts as separate energy functions. Comet represents both global concepts as well as objects under a unified framework.
  arXiv  Detail & Related papers  (2021-11-04T17:46:12Z)
• Visual Concept Reasoning Networks [93.99840807973546]
  A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. We propose to exploit this strategy and combine it with our Visual Concept Reasoning Networks (VCRNet) to enable reasoning between high-level visual concepts. Our proposed model, VCRNet, consistently improves the performance by increasing the number of parameters by less than 1%.
  arXiv  Detail & Related papers  (2020-08-26T20:02:40Z)
• 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)
• Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors [24.581839689833572]
  Convolutional neural network (CNN) models for computer vision are powerful but lack explainability in their most basic form. Recent work on explanations through feature importance of approximate linear models has moved from input-level features to features from mid-layer feature maps in the form of concept activation vectors (CAVs) In this work, we rethink the ACE algorithm of Ghorbani etal., proposing an alternative invertible concept-based explanation (ICE) framework to overcome its shortcomings.
  arXiv  Detail & Related papers  (2020-06-27T17:57:26Z)

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.