Convolutional Dynamic Alignment Networks for Interpretable Classifications

• URL: http://arxiv.org/abs/2104.00032v2
• Date: Mon, 15 Jan 2024 08:33:14 GMT
• Title: Convolutional Dynamic Alignment Networks for Interpretable Classifications
• Authors: Moritz B\"ohle and Mario Fritz and Bernt Schiele
• Abstract summary: We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA-Nets) Their core building blocks are Dynamic Alignment Units (DAUs), which linearly transform their input with weight vectors that dynamically align with task-relevant patterns. CoDA-Nets model the classification prediction through a series of input-dependent linear transformations, allowing for linear decomposition of the output into individual input contributions.
• Score: 108.83345790813445
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA-Nets), which are performant classifiers with a high degree of inherent interpretability. Their core building blocks are Dynamic Alignment Units (DAUs), which linearly transform their input with weight vectors that dynamically align with task-relevant patterns. As a result, CoDA-Nets model the classification prediction through a series of input-dependent linear transformations, allowing for linear decomposition of the output into individual input contributions. Given the alignment of the DAUs, the resulting contribution maps align with discriminative input patterns. These model-inherent decompositions are of high visual quality and outperform existing attribution methods under quantitative metrics. Further, CoDA-Nets constitute performant classifiers, achieving on par results to ResNet and VGG models on e.g. CIFAR-10 and TinyImagenet.

Related papers

• Domain-decomposed image classification algorithms using linear discriminant analysis and convolutional neural networks [0.0]
  Two different domain decomposed CNN models are experimentally compared for different image classification problems. The resulting models show improved classification accuracies compared to the corresponding, composed global CNN model. A novel decomposed LDA strategy is proposed which also relies on a localization approach and which is combined with a small neural network model.
  arXiv  Detail & Related papers  (2024-10-30T18:07:12Z)
• Principal Orthogonal Latent Components Analysis (POLCA Net) [0.27309692684728604]
  representation learning aims to learn features that are more useful and relevant for tasks such as classification, prediction, and clustering. We introduce Principal Orthogonal Latent Components Analysis Network (POLCA Net), an approach to mimic and extend PCA and LDA capabilities to non-linear domains.
  arXiv  Detail & Related papers  (2024-10-09T14:04:31Z)
• Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
  Modelling long-range dependencies is critical for scene understanding tasks in computer vision. A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive. We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
  arXiv  Detail & Related papers  (2022-09-20T14:41:37Z)
• Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling [65.40672505658213]
  We propose a novel deep neural network, namely Category-Aware feature alignment and Pseudo-Labelling Network (CAPL-Net) for UDA nuclei instance segmentation and classification. Our approach outperforms state-of-the-art UDA methods with a remarkable margin.
  arXiv  Detail & Related papers  (2022-07-04T07:05:06Z)
• B-cos Networks: Alignment is All We Need for Interpretability [136.27303006772294]
  We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. A B-cos transform induces a single linear transform that faithfully summarises the full model computations. We show that it can easily be integrated into common models such as VGGs, ResNets, InceptionNets, and DenseNets.
  arXiv  Detail & Related papers  (2022-05-20T16:03:29Z)
• Dynamically-Scaled Deep Canonical Correlation Analysis [77.34726150561087]
  Canonical Correlation Analysis (CCA) is a method for feature extraction of two views by finding maximally correlated linear projections of them. We introduce a novel dynamic scaling method for training an input-dependent canonical correlation model.
  arXiv  Detail & Related papers  (2022-03-23T12:52:49Z)
• Optimising for Interpretability: Convolutional Dynamic Alignment Networks [108.83345790813445]
  We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA Nets) Their core building blocks are Dynamic Alignment Units (DAUs), which are optimised to transform their inputs with dynamically computed weight vectors that align with task-relevant patterns. CoDA Nets model the classification prediction through a series of input-dependent linear transformations, allowing for linear decomposition of the output into individual input contributions.
  arXiv  Detail & Related papers  (2021-09-27T12:39:46Z)
• Class-Attentive Diffusion Network for Semi-Supervised Classification [27.433021864424266]
  Class-Attentive Diffusion Network (CAD-Net) is a graph neural network for semi-supervised classification. In this paper, we propose a new aggregation scheme that adaptively aggregates nodes probably of the same class among K-hop neighbors. Our experiments on seven benchmark datasets consistently demonstrate the efficacy of the proposed method.
  arXiv  Detail & Related papers  (2020-06-18T01:14:08Z)
• Multi-view Self-Constructing Graph Convolutional Networks with Adaptive Class Weighting Loss for Semantic Segmentation [23.623276007011373]
  We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation. We leverage multiple views in order to explicitly exploit the rotational invariance in airborne images. We demonstrate the effectiveness and flexibility of the proposed method on the Agriculture-Vision challenge and our model achieves very competitive results.
  arXiv  Detail & Related papers  (2020-04-21T22:18:16Z)

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.