A-FMI: Learning Attributions from Deep Networks via Feature Map Importance

• URL: http://arxiv.org/abs/2104.05527v1
• Date: Mon, 12 Apr 2021 14:54:44 GMT
• Title: A-FMI: Learning Attributions from Deep Networks via Feature Map Importance
• Authors: An Zhang, Xiang Wang, Chengfang Fang, Jie Shi, Tat-seng Chua, Zehua Chen
• Abstract summary: Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs) The redundancy of attribution features and the gradient saturation problem are challenges that attribution methods still face. We propose a new concept, feature map importance (FMI), to refine the contribution of each feature map, and a novel attribution method via FMI, to address the gradient saturation problem.
• Score: 58.708607977437794
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs). However, the redundancy of attribution features and the gradient saturation problem, which weaken the ability to identify significant features and cause an explanation focus shift, are challenges that attribution methods still face. In this work, we propose: 1) an essential characteristic, Strong Relevance, when selecting attribution features; 2) a new concept, feature map importance (FMI), to refine the contribution of each feature map, which is faithful to the CNN model; and 3) a novel attribution method via FMI, termed A-FMI, to address the gradient saturation problem, which couples the target image with a reference image, and assigns the FMI to the difference-from-reference at the granularity of feature map. Through visual inspections and qualitative evaluations on the ImageNet dataset, we show the compelling advantages of A-FMI on its faithfulness, insensitivity to the choice of reference, class discriminability, and superior explanation performance compared with popular attribution methods across varying CNN architectures.

Related papers

• Intuitionistic Fuzzy Cognitive Maps for Interpretable Image Classification [2.130156029408832]
  This paper introduces a novel framework, named Interpretable Intuitionistic FCM (I2FCM) which is domain-independent, simple to implement, and can be applied on CNN models. To the best of our knowledge this is the first time iFCMs are applied for image classification.
  arXiv  Detail & Related papers  (2024-08-07T12:58:39Z)
• SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization [24.286426387100423]
  We propose a method that captures subtle changes by aggregating context-aware features from most relevant image-regions. Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs) It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.
  arXiv  Detail & Related papers  (2022-09-05T19:43:15Z)
• On Exploring Pose Estimation as an Auxiliary Learning Task for Visible-Infrared Person Re-identification [66.58450185833479]
  In this paper, we exploit Pose Estimation as an auxiliary learning task to assist the VI-ReID task in an end-to-end framework. By jointly training these two tasks in a mutually beneficial manner, our model learns higher quality modality-shared and ID-related features. Experimental results on two benchmark VI-ReID datasets show that the proposed method consistently improves state-of-the-art methods by significant margins.
  arXiv  Detail & Related papers  (2022-01-11T09:44:00Z)
• 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)
• Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution [89.1947690981471]
  We propose a purposeful and interpretable detail-fidelity attention network to progressively process smoothes and details in divide-and-conquer manner. Particularly, we propose a Hessian filtering for interpretable feature representation which is high-profile for detail inference. Experiments demonstrate that the proposed methods achieve superior performances over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-09-28T08:31:23Z)
• Ventral-Dorsal Neural Networks: Object Detection via Selective Attention [51.79577908317031]
  We propose a new framework called Ventral-Dorsal Networks (VDNets) Inspired by the structure of the human visual system, we propose the integration of a "Ventral Network" and a "Dorsal Network" Our experimental results reveal that the proposed method outperforms state-of-the-art object detection approaches.
  arXiv  Detail & Related papers  (2020-05-15T23:57:36Z)
• Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution [27.48620879003556]
  We present a new learning framework that automatically learns the latent relationships of AUs via establishing semantic correspondences between feature maps. In the heatmap regression-based network, feature maps preserve rich semantic information associated with AU intensities and locations. This motivates us to model the correlation among feature channels, which implicitly represents the co-occurrence relationship of AU intensity levels.
  arXiv  Detail & Related papers  (2020-04-20T23:55:30Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)
• Relational Deep Feature Learning for Heterogeneous Face Recognition [17.494718795454055]
  We propose a graph-structured module called Graph Module (NIR) that extracts global relational information in addition to general facial features. The proposed method outperforms other state-of-the-art methods on five Heterogeneous Face Recognition (HFR) databases.
  arXiv  Detail & Related papers  (2020-03-02T07:35:23Z)

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.