# Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping

Source: [Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d68f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:48:10.793Z

Authors: Kira Vinogradova, Alexandr Dibrov, Gene Myers

Published: 2020-02-26T12:32:40.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.11434>)

[PDF](<https://arxiv.org/pdf/2002.11434.pdf>)