Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping

Abstract

Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been suggested for image classification, the interpretation of image segmentation still remains largely unexplored. To that end, we propose SEG-GRAD-CAM, a gradient-based method for interpreting semantic segmentation. Our method is an extension of the widely-used Grad-CAM method, applied locally to produce heatmaps showing the relevance of individual pixels for semantic segmentation.

2 pages, 2 figures. AAAI 2020 camera-ready

References in corpus (1)

• Methods for Interpreting and Understanding Deep Neural Networks

Cited by in corpus (10)

• U-Noise: Learnable Noise Masks for Interpretable Image Segmentation
• Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysis
• Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning
• Learning Metal Microstructural Heterogeneity through Spatial Mapping of Diffraction Latent Space Features
• Guiding the underwater acoustic target recognition with interpretable contrastive learning
• Interpreting a Semantic Segmentation Model for Coastline Detection
• Learning Debiased and Disentangled Representations for Semantic Segmentation
• Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation
• Reliable Explainability of Deep Learning Spatial-Spectral Classifiers for Improved Semantic Segmentation in Autonomous Driving
• Trustworthy AI-based crack-tip segmentation using domain-guided explanations