Cover Image

Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sarkar, Syamantak, Bora, Revoti P., Kaushal, Bhupender, George, Sudhish N, Raja, Kiran
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CF-CAM: Cluster Filter Class Activation Mapping for Reliable Gradient-Based Interpretability
by: He, Hongjie, et al.
Published: (2025)

Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations
by: Dekdegue, Hajar, et al.
Published: (2026)

Localized Region Guidance for Class Activation Mapping in WSSS
by: Torabi, Ali, et al.
Published: (2025)

Multi-view Feature Augmentation with Adaptive Class Activation Mapping
by: Gao, Xiang, et al.
Published: (2022)

Metric-Guided Synthesis of Class Activation Mapping
by: Luque-Cerpa, Alejandro, et al.
Published: (2025)

VoD: Learning Volume of Differences for Video-Based Deepfake Detection
by: Xu, Ying, et al.
Published: (2025)

DOEI: Dual Optimization of Embedding Information for Attention-Enhanced Class Activation Maps
by: Zhu, Hongjie, et al.
Published: (2025)

CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation
by: Wang, Jun, et al.
Published: (2022)

Class Visualizations and Activation Atlases for Enhancing Interpretability in Deep Learning-Based Computational Pathology
by: Gustav, Marco, et al.
Published: (2026)

Rank-Aware Quantile Activation for Motion-Robust Crop Segmentation in UAV Imagery
by: Kiran, Abinav, et al.
Published: (2026)

3VL: Using Trees to Improve Vision-Language Models' Interpretability
by: Yellinek, Nir, et al.
Published: (2023)

Interpretable Underwater Diver Gesture Recognition
by: Mangalvedhekar, Sudeep, et al.
Published: (2023)

TTE-CAM: Self-Explainable Class Activation Maps for Pretrained Black-Box CNNs
by: Djoumessi, Kerol, et al.
Published: (2026)

PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization
by: Guichemerre, Alexis, et al.
Published: (2025)

Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability
by: Oikarinen, Tuomas, et al.
Published: (2025)

Decom--CAM: Tell Me What You See, In Details! Feature-Level Interpretation via Decomposition Class Activation Map
by: Yang, Yuguang, et al.
Published: (2023)

Towards minimizing efforts for Morphing Attacks -- Deep embeddings for morphing pair selection and improved Morphing Attack Detection
by: Kessler, Roman, et al.
Published: (2023)

FaceOracle: Chat with a Face Image Oracle
by: Kabbani, Wassim, et al.
Published: (2025)

Demographic Variability in Face Image Quality Measures
by: Kabbani, Wassim, et al.
Published: (2025)

Region-CAM: Towards Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Tasks
by: Cai, Qingdong, et al.
Published: (2025)

CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos
by: Belharbi, Soufiane, et al.
Published: (2023)

Interpretable Zero-shot Learning with Infinite Class Concepts
by: Ye, Zihan, et al.
Published: (2025)

TextCAM: Explaining Class Activation Map with Text
by: Zhao, Qiming, et al.
Published: (2025)

Towards Robust and Reliable Concept Representations: Reliability-Enhanced Concept Embedding Model
by: Cai, Yuxuan, et al.
Published: (2025)

AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs
by: Chowdhury, Sanjoy, et al.
Published: (2025)

Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer
by: Nguyen, Quoc Khanh, et al.
Published: (2024)

Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps
by: Oh, Yoojin, et al.
Published: (2025)

Unsupervised Out-of-Distribution Detection in Medical Imaging Using Multi-Exit Class Activation Maps and Feature Masking
by: Chen, Yu-Jen, et al.
Published: (2025)

NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training
by: Tao, Yiyi, et al.
Published: (2024)

ACPV-Net: All-Class Polygonal Vectorization for Seamless Vector Map Generation from Aerial Imagery
by: Jiao, Weiqin, et al.
Published: (2026)

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability
by: He, Zhenghao, et al.
Published: (2025)

Open-Set Object Detection By Aligning Known Class Representations
by: Sarkar, Hiran, et al.
Published: (2024)

Benchmarking Class Activation Map Methods for Explainable Brain Hemorrhage Classification on Hemorica Dataset
by: Rafati, Z., et al.
Published: (2025)

Reduction of Class Activation Uncertainty with Background Information
by: Kabir, H M Dipu
Published: (2023)

Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models
by: Agrawal, Susmit, et al.
Published: (2025)

ViM-Disparity: Bridging the Gap of Speed, Accuracy and Memory for Disparity Map Generation
by: Bora, Maheswar, et al.
Published: (2024)

L2B: Learning to Bootstrap Robust Models for Combating Label Noise
by: Zhou, Yuyin, et al.
Published: (2022)

Interpreting Low-level Vision Models with Causal Effect Maps
by: Hu, Jinfan, et al.
Published: (2024)

ChatGPT Encounters Morphing Attack Detection: Zero-Shot MAD with Multi-Modal Large Language Models and General Vision Models
by: Zhang, Haoyu, et al.
Published: (2025)

Safer Skin Lesion Classification with Global Class Activation Probability Map Evaluation and SafeML
by: Paxton, Kuniko, et al.
Published: (2025)