Generalizing GradCAM for Embedding Networks

Mudit Bachhawat
2/1/2024
cs.CV

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network

83% match2025

A Novel Riemannian Sparse Representation Learning Network for Polarimetric SAR Image Classification

82% match2025

Bilinear-Convolutional Neural Network Using a Matrix Similarity-based Joint Loss Function for Skin Disease Classification

82% match2024

Leveraging Activations for Superpixel Explanations

81% match2024

KPCA-CAM: Visual Explainability of Deep Computer Vision Models using Kernel PCA

81% match1 repo12.9k2024

Survey on Embedding Models for Knowledge Graph and its Applications

81% match2024

Cite this paper

@article{bachhawat2024generalizing,
  title  = {Generalizing GradCAM for Embedding Networks},
  author = {Mudit Bachhawat},
  year   = {2024},
  eprint = {2402.00909},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.00909v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.00909.svg)](https://codeofpaper.com/paper/2402.00909)

Discussion