# Eigen-CAM: Class Activation Map using Principal Components

arXiv: https://arxiv.org/abs/2008.00299 · HTML: https://mlsanity.com/paper/2008.00299/

## Key facts

- Cited by 189 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2020.

## Built on by (most cited first, 30 of 189)

- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Large Selective Kernel Network for Remote Sensing Object Detection](https://mlsanity.com/paper/2303.09030/) (2023)
- [LSKNet: A Foundation Lightweight Backbone for Remote Sensing](https://mlsanity.com/paper/2403.11735/) (2024)
- [CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning](https://mlsanity.com/paper/2112.00686/) (2021)
- [Character-Centric Story Visualization via Visual Planning and Token Alignment](https://mlsanity.com/paper/2210.08465/) (2022)
- [Prioritized Semantic Learning for Zero-shot Instance Navigation](https://mlsanity.com/paper/2403.11650/) (2024)
- [Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling](https://mlsanity.com/paper/2301.01006/) (2023)
- [Opti-CAM: Optimizing saliency maps for interpretability](https://mlsanity.com/paper/2301.07002/) (2023)
- [Discovering Transferable Forensic Features for CNN-generated Images Detection](https://mlsanity.com/paper/2208.11342/) (2022)
- [FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation](https://mlsanity.com/paper/2310.07473/) (2023)
- [OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning](https://mlsanity.com/paper/2209.04851/) (2022)
- [Custom Structure Preservation in Face Aging](https://mlsanity.com/paper/2207.11025/) (2022)
- [Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition](https://mlsanity.com/paper/2107.03107/) (2021)
- [Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks](https://mlsanity.com/paper/2206.03826/) (2022)
- [SATr: Slice Attention with Transformer for Universal Lesion Detection](https://mlsanity.com/paper/2203.07373/) (2022)
- [Neural Networks are Decision Trees](https://mlsanity.com/paper/2210.05189/) (2022)
- [Large-scale Long-tailed Disease Diagnosis on Radiology Images](https://mlsanity.com/paper/2312.16151/) (2023)
- [Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming](https://mlsanity.com/paper/2206.10816/) (2022)
- [Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racing](https://mlsanity.com/paper/2210.14985/) (2022)
- [Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation](https://mlsanity.com/paper/2501.11309/) (2025)
- [Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection](https://mlsanity.com/paper/2501.03775/) (2025)
- [Test-Time Backdoor Detection for Object Detection Models](https://mlsanity.com/paper/2503.15293/) (2025)
- [LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks](https://mlsanity.com/paper/2402.12525/) (2024)
- [Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation](https://mlsanity.com/paper/2406.05704/) (2024)
- [Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification](https://mlsanity.com/paper/2211.17161/) (2022)
- [Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching](https://mlsanity.com/paper/2301.00131/) (2022)
- [Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis](https://mlsanity.com/paper/2501.09333/) (2025)
- [Saliency Cards: A Framework to Characterize and Compare Saliency Methods](https://mlsanity.com/paper/2206.02958/) (2022)
- [Dynamic Adversarial Attacks on Autonomous Driving Systems](https://mlsanity.com/paper/2312.06701/) (2023)

## Abstract (arXiv)

Deep neural networks are ubiquitous due to the ease of developing models and their influence on other domains. At the heart of this progress is convolutional neural networks (CNNs) that are capable of learning representations or features given a set of data. Making sense of such complex models (i.e., millions of parameters and hundreds of layers) remains challenging for developers as well as the end-users. This is partially due to the lack of tools or interfaces capable of providing interpretability and transparency. A growing body of literature, for example, class activation map (CAM), focuses on making sense of what a model learns from the data or why it behaves poorly in a given task. This paper builds on previous ideas to cope with the increasing demand for interpretable, robust, and transparent models. Our approach provides a simpler and intuitive (or familiar) way of generating CAM. The proposed Eigen-CAM computes and visualizes the principle components of the learned features/representations from the convolutional layers. Empirical studies were performed to compare the Eigen-CAM with the state-of-the-art methods (such as Grad-CAM, Grad-CAM++, CNN-fixations) by evaluating on benchmark datasets such as weakly-supervised localization and localizing objects in the presence of adversarial noise. Eigen-CAM was found to be robust against classification errors made by fully connected layers in CNNs, does not rely on the backpropagation of gradients, class relevance score, maximum activation locations, or any other form of weighting features. In addition, it works with all CNN models without the need to modify layers or retrain models. Empirical results show up to 12% improvement over the best method among the methods compared on weakly supervised object localization.