Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations

• URL: http://arxiv.org/abs/2303.10523v2
• Date: Mon, 25 Sep 2023 11:27:02 GMT
• Title: Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations
• Authors: Alexandros Doumanoglou, Stylianos Asteriadis, Dimitrios Zarpalas
• Abstract summary: We show that, intermediate layer representations become more interpretable when transformed to the bases extracted with our method. We compare the bases extracted with our method with the bases derived with a supervised approach and find that, in one aspect, the proposed unsupervised approach has a strength that constitutes a limitation of the supervised one and give potential directions for future research.
• Score: 53.973055975918655
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human understandable concepts. In this work, we expand on previous works in the literature that use annotated concept datasets to extract interpretable feature space directions and propose an unsupervised post-hoc method to extract a disentangling interpretable basis by looking for the rotation of the feature space that explains sparse one-hot thresholded transformed representations of pixel activations. We do experimentation with existing popular CNNs and demonstrate the effectiveness of our method in extracting an interpretable basis across network architectures and training datasets. We make extensions to the existing basis interpretability metrics found in the literature and show that, intermediate layer representations become more interpretable when transformed to the bases extracted with our method. Finally, using the basis interpretability metrics, we compare the bases extracted with our method with the bases derived with a supervised approach and find that, in one aspect, the proposed unsupervised approach has a strength that constitutes a limitation of the supervised one and give potential directions for future research.

Related papers

• Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts [68.48103545146127]
  This paper proposes a novel framework for unsupervised exploration of diffusion latent spaces. We directly leverage natural language prompts and image captions to map latent directions. Our method provides a more scalable and interpretable understanding of the semantic knowledge encoded within diffusion models.
  arXiv  Detail & Related papers  (2024-10-25T21:44:51Z)
• Uncovering Unique Concept Vectors through Latent Space Decomposition [0.0]
  Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution estimates. We propose a novel post-hoc unsupervised method that automatically uncovers the concepts learned by deep models during training. Our experiments reveal that the majority of our concepts are readily understandable to humans, exhibit coherency, and bear relevance to the task at hand.
  arXiv  Detail & Related papers  (2023-07-13T17:21:54Z)
• Adversarial Attacks on the Interpretation of Neuron Activation Maximization [70.5472799454224]
  Activation-maximization approaches are used to interpret and analyze trained deep-learning models. In this work, we consider the concept of an adversary manipulating a model for the purpose of deceiving the interpretation.
  arXiv  Detail & Related papers  (2023-06-12T19:54:33Z)
• From Patches to Objects: Exploiting Spatial Reasoning for Better Visual Representations [2.363388546004777]
  We propose a novel auxiliary pretraining method that is based on spatial reasoning. Our proposed method takes advantage of a more flexible formulation of contrastive learning by introducing spatial reasoning as an auxiliary task for discriminative self-supervised methods.
  arXiv  Detail & Related papers  (2023-05-21T07:46:46Z)
• Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations [14.77637281844823]
  We propose the post-hoc eXplainable Artificial Intelligence method L-CRP to generate explanations that automatically identify and visualize relevant concepts learned, recognized and used by the model during inference as well as precisely locate them in input space. We verify the faithfulness of our proposed technique by quantitatively comparing different concept attribution methods, and discuss the effect on explanation complexity on popular datasets such as CityScapes, Pascal VOC and MS COCO 2017.
  arXiv  Detail & Related papers  (2022-11-21T13:12:23Z)
• Discriminative Attribution from Counterfactuals [64.94009515033984]
  We present a method for neural network interpretability by combining feature attribution with counterfactual explanations. We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
  arXiv  Detail & Related papers  (2021-09-28T00:53:34Z)
• Self-supervised Segmentation via Background Inpainting [96.10971980098196]
  We introduce a self-supervised detection and segmentation approach that can work with single images captured by a potentially moving camera. We exploit a self-supervised loss function that we exploit to train a proposal-based segmentation network. We apply our method to human detection and segmentation in images that visually depart from those of standard benchmarks and outperform existing self-supervised methods.
  arXiv  Detail & Related papers  (2020-11-11T08:34:40Z)
• Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation [22.688772441351308]
  Methods based on class activation mapping and randomized input sampling have gained great popularity. However, the attribution methods provide lower resolution and blurry explanation maps that limit their explanation power. In this work, we collect visualization maps from multiple layers of the model based on an attribution-based input sampling technique. We also propose a layer selection strategy that applies to the whole family of CNN-based models.
  arXiv  Detail & Related papers  (2020-10-01T20:27:30Z)
• 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)
• Ontology-based Interpretable Machine Learning for Textual Data [35.01650633374998]
  We introduce a novel interpreting framework that learns an interpretable model based on sampling technique to explain prediction models. To narrow down the search space for explanations, we design a learnable anchor algorithm. A set of regulations is further introduced, regarding combining learned interpretable representations with anchors to generate comprehensible explanations.
  arXiv  Detail & Related papers  (2020-04-01T02:51:57Z)

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.