Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations

• URL: http://arxiv.org/abs/2207.05902v1
• Date: Wed, 13 Jul 2022 00:26:56 GMT
• Title: Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations
• Authors: Satoshi Munakata, Caterina Urban, Haruki Yokoyama, Koji Yamamoto, and Kazuki Munakata
• Abstract summary: Saliency-maps are used to check the validity of the classification decision basis. We propose the first verification method for attention robustness, i.e., the local robustness of the changes in the saliency-map against combinations of semantic perturbations.
• Score: 2.7598466876818004
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: It is known that deep neural networks (DNNs) classify an input image by paying particular attention to certain specific pixels; a graphical representation of the magnitude of attention to each pixel is called a saliency-map. Saliency-maps are used to check the validity of the classification decision basis, e.g., it is not a valid basis for classification if a DNN pays more attention to the background rather than the subject of an image. Semantic perturbations can significantly change the saliency-map. In this work, we propose the first verification method for attention robustness, i.e., the local robustness of the changes in the saliency-map against combinations of semantic perturbations. Specifically, our method determines the range of the perturbation parameters (e.g., the brightness change) that maintains the difference between the actual saliency-map change and the expected saliency-map change below a given threshold value. Our method is based on activation region traversals, focusing on the outermost robust boundary for scalability on larger DNNs. Experimental results demonstrate that our method can show the extent to which DNNs can classify with the same basis regardless of semantic perturbations and report on performance and performance factors of activation region traversals.

Related papers

• SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training [10.716021768803433]
  Saliency map is a common form of explanation illustrating the heatmap of feature attributions. We propose a model-agnostic learning method called Saliency Constrained Adaptive Adversarial Training (SCAAT) to improve the quality of such DNN interpretability.
  arXiv  Detail & Related papers  (2023-11-09T04:48:38Z)
• Fine-grained Recognition with Learnable Semantic Data Augmentation [68.48892326854494]
  Fine-grained image recognition is a longstanding computer vision challenge. We propose diversifying the training data at the feature-level to alleviate the discriminative region loss problem. Our method significantly improves the generalization performance on several popular classification networks.
  arXiv  Detail & Related papers  (2023-09-01T11:15:50Z)
• 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)
• Weakly-supervised fire segmentation by visualizing intermediate CNN layers [82.75113406937194]
  Fire localization in images and videos is an important step for an autonomous system to combat fire incidents. We consider weakly supervised segmentation of fire in images, in which only image labels are used to train the network. We show that in the case of fire segmentation, which is a binary segmentation problem, the mean value of features in a mid-layer of classification CNN can perform better than conventional Class Activation Mapping (CAM) method.
  arXiv  Detail & Related papers  (2021-11-16T11:56:28Z)
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency [61.40511574314069]
  Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
  arXiv  Detail & Related papers  (2021-06-20T08:20:56Z)
• Bayesian Attention Belief Networks [59.183311769616466]
  Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. This paper introduces Bayesian attention belief networks, which construct a decoder network by modeling unnormalized attention weights. We show that our method outperforms deterministic attention and state-of-the-art attention in accuracy, uncertainty estimation, generalization across domains, and adversarial attacks.
  arXiv  Detail & Related papers  (2021-06-09T17:46:22Z)
• Focused LRP: Explainable AI for Face Morphing Attack Detection [3.145455301228176]
  We present a framework to explain to a human inspector on a precise pixel level, which image regions are used by a Deep Neural Network to distinguish between a genuine and a morphed face image. We also propose a framework to objectively analyze the quality of our method and compare FLRP to other interpretability methods.
  arXiv  Detail & Related papers  (2021-03-26T19:05:01Z)
• An Empirical Method to Quantify the Peripheral Performance Degradation in Deep Networks [18.808132632482103]
  convolutional neural network (CNN) kernels compound with each convolutional layer. Deeper and deeper networks combined with stride-based down-sampling means that the propagation of this region can end up covering a non-negligable portion of the image. Our dataset is constructed by inserting objects into high resolution backgrounds, thereby allowing us to crop sub-images which place target objects at specific locations relative to the image border. By probing the behaviour of Mask R-CNN across a selection of target locations, we see clear patterns of performance degredation near the image boundary, and in particular in the image corners.
  arXiv  Detail & Related papers  (2020-12-04T18:00:47Z)
• Semantic Change Detection with Asymmetric Siamese Networks [71.28665116793138]
  Given two aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries. This problem is vital in many earth vision related tasks, such as precise urban planning and natural resource management. We present an asymmetric siamese network (ASN) to locate and identify semantic changes through feature pairs obtained from modules of widely different structures.
  arXiv  Detail & Related papers  (2020-10-12T13:26:30Z)
• Deep Convolutional Neural Network for Identifying Seam-Carving Forgery [10.324492319976798]
  We propose a convolutional neural network (CNN)-based approach to classifying seam-carving-based image for reduction and expansion. Our work exhibits state-of-the-art performance in terms of three-class classification (original, seam inserted, and seam removed)
  arXiv  Detail & Related papers  (2020-07-05T17:20:51Z)
• 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)

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.