SOTAVerified

Generalizing GradCAM for Embedding Networks

2024-02-01Code Available0· sign in to hype

Mudit Bachhawat

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Visualizing CNN is an important part in building trust and explaining model's prediction. Methods like CAM and GradCAM have been really successful in localizing area of the image responsible for the output but are only limited to classification models. In this paper, we present a new method EmbeddingCAM, which generalizes the Grad-CAM for embedding networks. We show that for classification networks, EmbeddingCAM reduces to GradCAM. We show the effectiveness of our method on CUB-200-2011 dataset and also present quantitative and qualitative analysis on the dataset.

Tasks

Reproductions