Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces

• URL: http://arxiv.org/abs/2305.07663v2
• Date: Tue, 27 Jun 2023 09:56:30 GMT
• Title: Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces
• Authors: Georgii Mikriukov, Gesina Schwalbe, Christian Hellert and Korinna Bade
• Abstract summary: Safety-critical applications require transparency in artificial intelligence components. convolutional neural networks (CNNs) widely used for perception tasks lack inherent interpretability. We propose two methods for estimating the layer-wise similarity between semantic information inside CNN latent spaces.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Safety-critical applications require transparency in artificial intelligence (AI) components, but widely used convolutional neural networks (CNNs) widely used for perception tasks lack inherent interpretability. Hence, insights into what CNNs have learned are primarily based on performance metrics, because these allow, e.g., for cross-architecture CNN comparison. However, these neglect how knowledge is stored inside. To tackle this yet unsolved problem, our work proposes two methods for estimating the layer-wise similarity between semantic information inside CNN latent spaces. These allow insights into both the flow and likeness of semantic information within CNN layers, and into the degree of their similarity between different network architectures. As a basis, we use two renowned explainable artificial intelligence (XAI) techniques, which are used to obtain concept activation vectors, i.e., global vector representations in the latent space. These are compared with respect to their activation on test inputs. When applied to three diverse object detectors and two datasets, our methods reveal that (1) similar semantic concepts are learned regardless of the CNN architecture, and (2) similar concepts emerge in similar relative layer depth, independent of the total number of layers. Finally, our approach poses a promising step towards semantic model comparability and comprehension of how different CNNs process semantic information.

Related papers

• Linking in Style: Understanding learned features in deep learning models [0.0]
  Convolutional neural networks (CNNs) learn abstract features to perform object classification. We propose an automatic method to visualize and systematically analyze learned features in CNNs.
  arXiv  Detail & Related papers  (2024-09-25T12:28:48Z)
• Feature CAM: Interpretable AI in Image Classification [2.4409988934338767]
  There is a lack of trust to use Artificial Intelligence in critical and high-precision fields such as security, finance, health, and manufacturing industries. We introduce a novel technique Feature CAM, which falls in the perturbation-activation combination, to create fine-grained, class-discriminative visualizations. The resulting saliency maps proved to be 3-4 times better human interpretable than the state-of-the-art in ABM.
  arXiv  Detail & Related papers  (2024-03-08T20:16:00Z)
• A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations [0.0]
  Convolutional neural networks (CNNs) are one of the most successful computer vision systems to solve object recognition. Yet it remains poorly understood how CNNs actually make their decisions, what the nature of their internal representations is, and how their recognition strategies differ from humans.
  arXiv  Detail & Related papers  (2022-12-12T16:40:29Z)
• Visual Recognition with Deep Nearest Centroids [57.35144702563746]
  We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective network for large-scale visual recognition. Compared with parametric counterparts, DNC performs better on image classification (CIFAR-10, ImageNet) and greatly boots pixel recognition (ADE20K, Cityscapes)
  arXiv  Detail & Related papers  (2022-09-15T15:47:31Z)
• Comparison Analysis of Traditional Machine Learning and Deep Learning Techniques for Data and Image Classification [62.997667081978825]
  The purpose of the study is to analyse and compare the most common machine learning and deep learning techniques used for computer vision 2D object classification tasks. Firstly, we will present the theoretical background of the Bag of Visual words model and Deep Convolutional Neural Networks (DCNN) Secondly, we will implement a Bag of Visual Words model, the VGG16 CNN Architecture.
  arXiv  Detail & Related papers  (2022-04-11T11:34:43Z)
• Concept Embeddings for Fuzzy Logic Verification of Deep Neural Networks in Perception Tasks [1.2246649738388387]
  We present a simple, yet effective, approach to verify whether a trained convolutional neural network (CNN) respects specified symbolic background knowledge. The knowledge may consist of any fuzzy predicate logic rules. We show that this approach benefits from fuzziness and calibrating the concept outputs.
  arXiv  Detail & Related papers  (2022-01-03T10:35:47Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• The Mind's Eye: Visualizing Class-Agnostic Features of CNNs [92.39082696657874]
  We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most informative features of a specific layer. Our method uses a dual-objective activation and distance loss, without requiring a generator network nor modifications to the original model.
  arXiv  Detail & Related papers  (2021-01-29T07:46:39Z)
• Exploring the Interchangeability of CNN Embedding Spaces [0.5735035463793008]
  We map between 10 image-classification CNNs and between 4 facial-recognition CNNs. For CNNs trained to the same classes and sharing a common backend-logit architecture, a linear-mapping may always be calculated directly from the backend layer weights. The implications are far-reaching, suggesting an underlying commonality between representations learned by networks designed and trained for a common task.
  arXiv  Detail & Related papers  (2020-10-05T20:32:40Z)
• IAUnet: Global Context-Aware Feature Learning for Person Re-Identification [106.50534744965955]
  IAU block enables the feature to incorporate the globally spatial, temporal, and channel context. It is lightweight, end-to-end trainable, and can be easily plugged into existing CNNs to form IAUnet. Experiments show that IAUnet performs favorably against state-of-the-art on both image and video reID tasks.
  arXiv  Detail & Related papers  (2020-09-02T13:07:10Z)
• Architecture Disentanglement for Deep Neural Networks [174.16176919145377]
  We introduce neural architecture disentanglement (NAD) to explain the inner workings of deep neural networks (DNNs) NAD learns to disentangle a pre-trained DNN into sub-architectures according to independent tasks, forming information flows that describe the inference processes. Results show that misclassified images have a high probability of being assigned to task sub-architectures similar to the correct ones.
  arXiv  Detail & Related papers  (2020-03-30T08:34:33Z)

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.