CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency

• URL: http://arxiv.org/abs/2106.10649v1
• Date: Sun, 20 Jun 2021 08:20:56 GMT
• Title: CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency
• Authors: Mohammad A. A. K. Jalwana, Naveed Akhtar, Mohammed Bennamoun, Ajmal Mian
• Abstract summary: 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.
• Score: 61.40511574314069
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. However, class-insensitivity of the earlier layers in a network only allows saliency computation with low resolution activation maps of the deeper layers, resulting in compromised image saliency. Remedifying this can lead to sanity failures. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors and preserving the map sanity. Our method systematically performs multi-scale accumulation and fusion of the activation maps and backpropagated gradients to compute precise saliency maps. From accurate image saliency to articulation of relative importance of input features for different models, and precise discrimination between model perception of visually similar objects, our high-resolution mapping offers multiple novel insights into the black-box deep visual models, which are presented in the paper. We also demonstrate the utility of our saliency maps in adversarial setup by drastically reducing the norm of attack signals by focusing them on the precise regions identified by our maps. Our method also inspires new evaluation metrics and a sanity check for this developing research direction. Code is available here https://github.com/VisMIL/CAMERAS

Related papers

• Hi-Map: Hierarchical Factorized Radiance Field for High-Fidelity Monocular Dense Mapping [51.739466714312805]
  We introduce Hi-Map, a novel monocular dense mapping approach based on Neural Radiance Field (NeRF) Hi-Map is exceptional in its capacity to achieve efficient and high-fidelity mapping using only posed RGB inputs.
  arXiv  Detail & Related papers  (2024-01-06T12:32:25Z)
• Generating detailed saliency maps using model-agnostic methods [0.0]
  We focus on a model-agnostic explainability method called RISE, elaborate on observed shortcomings of its grid-based approach. modifications, collectively called VRISE (Voronoi-RISE), are meant to, respectively, improve the accuracy of maps generated using large occlusions. We compare accuracy of saliency maps produced by VRISE and RISE on the validation split of ILSVRC2012, using a saliency-guided content insertion/deletion metric and a localization metric based on bounding boxes.
  arXiv  Detail & Related papers  (2022-09-04T21:34:46Z)
• Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value [86.69600830581912]
  We develop a novel visual explanation method called Shap-CAM based on class activation mapping. We demonstrate that Shap-CAM achieves better visual performance and fairness for interpreting the decision making process.
  arXiv  Detail & Related papers  (2022-08-07T00:59:23Z)
• Abs-CAM: A Gradient Optimization Interpretable Approach for Explanation of Convolutional Neural Networks [7.71412567705588]
  Class activation mapping-based method has been widely used to interpret the internal decisions of models in computer vision tasks. We propose an Absolute value Class Activation Mapping-based (Abs-CAM) method, which optimize the gradients derived from the backpropagation. The framework of Abs-CAM is divided into two phases: generating initial saliency map and generating final saliency map.
  arXiv  Detail & Related papers  (2022-07-08T02:06:46Z)
• Subpixel Heatmap Regression for Facial Landmark Localization [65.41270740933656]
  Heatmap regression approaches suffer from discretization-induced errors related to both the heatmap encoding and decoding process. We propose a new approach for the heatmap encoding and decoding process by leveraging the underlying continuous distribution. Our approach offers noticeable gains across multiple datasets setting a new state-of-the-art result in facial landmark localization.
  arXiv  Detail & Related papers  (2021-11-03T17:21:28Z)
• Canonical Saliency Maps: Decoding Deep Face Models [47.036036069156104]
  We present 'Canonical Saliency Maps', a new method that highlights relevant facial areas by projecting saliency maps onto a canonical face model. Our results show the usefulness of the proposed canonical saliency maps, which can be used on any deep face model regardless of the architecture.
  arXiv  Detail & Related papers  (2021-05-04T09:42:56Z)
• iGOS++: Integrated Gradient Optimized Saliency by Bilateral Perturbations [31.72311989250957]
  Saliency maps are widely-used local explanation tools. We present iGOS++, a framework to generate saliency maps optimized for altering the output of the black-box system.
  arXiv  Detail & Related papers  (2020-12-31T18:04:12Z)
• Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps [78.2581910688094]
  This work introduces a novel self-enhancement method to harvest accurate object localization maps and object boundaries with only category labels as supervision. In particular, the proposed Self-Enhancement Maps achieve the state-of-the-art localization accuracy of 54.88% on ILSVRC.
  arXiv  Detail & Related papers  (2020-06-09T12:35:55Z)
• Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution [70.78655569298923]
  Integrated Gradients as an attribution method for deep neural network models offers simple implementability. It suffers from noisiness of explanations which affects the ease of interpretability. The SmoothGrad technique is proposed to solve the noisiness issue and smoothen the attribution maps of any gradient-based attribution method.
  arXiv  Detail & Related papers  (2020-04-22T10:43:19Z)

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.