Optimising for Interpretability: Convolutional Dynamic Alignment Networks

• URL: http://arxiv.org/abs/2109.13004v2
• Date: Mon, 15 Jan 2024 08:44:20 GMT
• Title: Optimising for Interpretability: Convolutional Dynamic Alignment Networks
• Authors: Moritz B\"ohle, Mario Fritz, 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 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.
• 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 are optimised to transform their inputs with dynamically computed weight vectors that 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. Lastly, CoDA Nets can be combined with conventional neural network models to yield powerful classifiers that more easily scale to complex datasets such as Imagenet whilst exhibiting an increased interpretable depth, i.e., the output can be explained well in terms of contributions from intermediate layers within the network.

Related papers

• SODAWideNet++: Combining Attention and Convolutions for Salient Object Detection [3.2586315449885106]
  We propose a novel encoder-decoder-style neural network called SODAWideNet++ designed explicitly for Salient Object Detection. Inspired by the vision transformers ability to attain a global receptive field from the initial stages, we introduce the Attention Guided Long Range Feature Extraction (AGLRFE) module. In contrast to the current paradigm of ImageNet pre-training, we modify 118K annotated images from the COCO semantic segmentation dataset by binarizing the annotations to pre-train the proposed model end-to-end.
  arXiv  Detail & Related papers  (2024-08-29T15:51:06Z)
• Neighborhood Convolutional Network: A New Paradigm of Graph Neural Networks for Node Classification [12.062421384484812]
  Graph Convolutional Network (GCN) decouples neighborhood aggregation and feature transformation in each convolutional layer. In this paper, we propose a new paradigm of GCN, termed Neighborhood Convolutional Network (NCN) In this way, the model could inherit the merit of decoupled GCN for aggregating neighborhood information, at the same time, develop much more powerful feature learning modules.
  arXiv  Detail & Related papers  (2022-11-15T02:02:51Z)
• 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)
• 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)
• Latent Code-Based Fusion: A Volterra Neural Network Approach [21.25021807184103]
  We propose a deep structure encoder using the recently introduced Volterra Neural Networks (VNNs) We show that the proposed approach demonstrates a much-improved sample complexity over CNN-based auto-encoder with a superb robust classification performance.
  arXiv  Detail & Related papers  (2021-04-10T18:29:01Z)
• Convolutional Dynamic Alignment Networks for Interpretable Classifications [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 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.
  arXiv  Detail & Related papers  (2021-03-31T18:03:53Z)
• Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration [65.11022516031463]
  We present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction. In this paper, we propose asymmetric co-attention (AsyCA) which is attached at each interleaved node to model the feature dependencies. Our presented DIN can be trained end-to-end and applied to various image restoration tasks.
  arXiv  Detail & Related papers  (2020-10-29T15:32:00Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation [23.623276007011373]
  We propose a module that learns a long-range dependency graph directly from the image and uses it to propagate contextual information efficiently. The module is optimised via a novel adaptive diagonal enhancement method and a variational lower bound. When incorporated into a neural network (SCG-Net), semantic segmentation is performed in an end-to-end manner and competitive performance.
  arXiv  Detail & Related papers  (2020-09-03T12:13:09Z)

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.