Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs
arXiv:2008.02312
Abstract
To have a better understanding and usage of Convolution Neural Networks (CNNs), the visualization and interpretation of CNNs has attracted increasing attention in recent years. In particular, several Class Activation Mapping (CAM) methods have been proposed to discover the connection between CNN's decision and image regions. In spite of the reasonable visualization, lack of clear and sufficient theoretical support is the main limitation of these methods. In this paper, we introduce two axioms -- Conservation and Sensitivity -- to the visualization paradigm of the CAM methods. Meanwhile, a dedicated Axiom-based Grad-CAM (XGrad-CAM) is proposed to satisfy these axioms as much as possible. Experiments demonstrate that XGrad-CAM is an enhanced version of Grad-CAM in terms of conservation and sensitivity. It is able to achieve better visualization performance than Grad-CAM, while also be class-discriminative and easy-to-implement compared with Grad-CAM++ and Ablation-CAM. The code is available at https://github.com/Fu0511/XGrad-CAM.
BMVC 2020 (Oral presentation). Code is avaliable at: https://github.com/Fu0511/XGrad-CAM
References in corpus (3)
Cited by in corpus (9)
- Explainable Model-Agnostic Similarity and Confidence in Face Verification
- How Will It Drape Like? Capturing Fabric Mechanics from Depth Images
- An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
- SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost
- On The Coherence of Quantitative Evaluation of Visual Explanations
- Gradient Frequency Modulation for Visually Explaining Video Understanding Models
- EDDA: Explanation-driven Data Augmentation to Improve Explanation Faithfulness
- PatchGame: Learning to Signal Mid-level Patches in Referential Games
- Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning