Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks

• URL: http://arxiv.org/abs/2011.08891v4
• Date: Sun, 21 Nov 2021 01:35:57 GMT
• Title: Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks
• Authors: Rachel Lea Draelos, Lawrence Carin
• Abstract summary: Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations. We illustrate a previously unrecognized limitation of the popular neural network explanation method Grad-CAM. We propose HiResCAM, a class-specific explanation method that is guaranteed to highlight only the locations the model used to make each prediction.
• Score: 89.56292219019163
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations. We illustrate a previously unrecognized limitation of the popular neural network explanation method Grad-CAM: as a side effect of the gradient averaging step, Grad-CAM sometimes highlights locations the model did not actually use. To solve this problem, we propose HiResCAM, a novel class-specific explanation method that is guaranteed to highlight only the locations the model used to make each prediction. We prove that HiResCAM is a generalization of CAM and explore the relationships between HiResCAM and other gradient-based explanation methods. Experiments on PASCAL VOC 2012, including crowd-sourced evaluations, illustrate that while HiResCAM's explanations faithfully reflect the model, Grad-CAM often expands the attention to create bigger and smoother visualizations. Overall, this work advances convolutional neural network explanation approaches and may aid in the development of trustworthy models for sensitive applications.

Related papers

• SIGMA:Sinkhorn-Guided Masked Video Modeling [69.31715194419091]
  Sinkhorn-guided Masked Video Modelling ( SIGMA) is a novel video pretraining method. We distribute features of space-time tubes evenly across a limited number of learnable clusters. Experimental results on ten datasets validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations.
  arXiv  Detail & Related papers  (2024-07-22T08:04:09Z)
• Generalizing GradCAM for Embedding Networks [0.0]
  We present a new method EmbeddingCAM, which generalizes the Grad-CAM for embedding networks. We show the effectiveness of our method on CUB-200-2011 dataset and also present quantitative and qualitative analysis on the dataset.
  arXiv  Detail & Related papers  (2024-02-01T04:58:06Z)
• BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications [69.22739434619531]
  We propose an outcome-agnostic CAM approach, called BroadCAM, for small-scale weakly supervised applications. By evaluating BroadCAM on VOC2012 and BCSS-WSSS for WSSS and OpenImages30k for WSOL, BroadCAM demonstrates superior performance.
  arXiv  Detail & Related papers  (2023-09-07T06:45:43Z)
• Empowering CAM-Based Methods with Capability to Generate Fine-Grained and High-Faithfulness Explanations [1.757194730633422]
  We propose FG-CAM, which extends CAM-based methods to enable generating fine-grained and high-faithfulness explanations. Our method not only solves the shortcoming of CAM-based methods without changing their characteristics, but also generates fine-grained explanations that have higher faithfulness than LRP and its variants.
  arXiv  Detail & Related papers  (2023-03-16T09:29:05Z)
• Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation [59.24824050194334]
  This paper turns to an interesting working mechanism in agent learning named Complementary Learning System ( CLS) Motivated by this simple but effective learning pattern, we propose a General-Specific Learning Mechanism (GSLM) GSLM develops a General Learning Module (GLM) and a Specific Learning Module (SLM)
  arXiv  Detail & Related papers  (2023-03-04T16:16:47Z)
• Recipro-CAM: Gradient-free reciprocal class activation map [0.0]
  We propose a lightweight architecture and gradient free Reciprocal CAM (Recipro-CAM) to exploit the correlation between activation maps and network outputs. With the proposed method, we achieved the gains of 1:78 - 3:72% in the ResNet family compared to Score-CAM. In addition, Recipro-CAM exhibits a saliency map generation rate similar to Grad-CAM and approximately 148 times faster than Score-CAM.
  arXiv  Detail & Related papers  (2022-09-28T13:15:03Z)
• 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)
• Explainable multiple abnormality classification of chest CT volumes with AxialNet and HiResCAM [89.2175350956813]
  We introduce the challenging new task of explainable multiple abnormality classification in volumetric medical images. We propose a multiple instance learning convolutional neural network, AxialNet, that allows identification of top slices for each abnormality. We then aim to improve the model's learning through a novel mask loss that leverages HiResCAM and 3D allowed regions.
  arXiv  Detail & Related papers  (2021-11-24T01:14:33Z)
• Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs [29.731732363623713]
  Class Activation Mapping (CAM) methods have been proposed to discover the connection between CNN's decision and image regions. In this paper, we introduce two axioms -- Conservation and Sensitivity -- to the visualization paradigm of the CAM methods. A dedicated Axiom-based Grad-CAM (XGrad-CAM) is proposed to satisfy these axioms as much as possible.
  arXiv  Detail & Related papers  (2020-08-05T18:42:33Z)

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.