Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention (original) (raw)
Related papers
Data Mining and Knowledge Discovery
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks
2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018
MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks
IEEE Transactions on Artificial Intelligence
Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism
Nikolaos Gkalelis, Ioanna Gkartzonika
2022
A Concept-Aware Explainability Method for Convolutional Neural Networks
Research Square (Research Square), 2024
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
2018
ADVISE: ADaptive Feature Relevance and VISual Explanations for Convolutional Neural Networks
arXiv (Cornell University), 2022
Exploiting auto-encoders for middle-level explanations of image classification systems
2021
Multi Layered Feature Explanation Method for Convolutional Neural Networks
Lecture Notes in Computer Science, 2022
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
International Journal of Computer Vision, 2019
Explaining Visual Classification using Attributes
2019 International Conference on Content-Based Multimedia Indexing (CBMI), 2019
Journal of Electronic Imaging, 2021
CDeepEx: Contrastive Deep Explanations
2020
Explaining Deep Learning Models for Structured Data using Layer-Wise Relevance Propagation
ArXiv, 2020
Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges
2018
Interpretable Basis Decomposition for Visual Explanation
Computer Vision – ECCV 2018, 2018
arXiv (Cornell University), 2023
Black Box Explanation by Learning Image Exemplars in the Latent Feature Space
Machine Learning and Knowledge Discovery in Databases, 2020
Towards Explainable Neural-Symbolic Visual Reasoning
arXiv: Learning, 2019
Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks
ArXiv, 2019
PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs
2021 International Joint Conference on Neural Networks (IJCNN), 2021
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020
Xplique: A Deep Learning Explainability Toolbox
Cornell University - arXiv, 2022
GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps
2021
Best of both worlds: local and global explanations with human-understandable concepts
2021
Interpretable Convolutional Neural Networks
Explainable Image Classification: The Journey So Far and the Road Ahead
AI
Assessing the Reliability of Visual Explanations of Deep Models with Adversarial Perturbations
2020 International Joint Conference on Neural Networks (IJCNN)
A Review on Explainability in Multimodal Deep Neural Nets
IEEE Access
Explaining Deep Learning Models for Tabular Data Using Layer-Wise Relevance Propagation
Applied Sciences, 2021
Learning Global Additive Explanations for Neural Nets Using Model Distillation
arXiv: Machine Learning, 2018
Cross-CAM: Focused Visual Explanations for Deep Convolutional Networks via Training-Set Tracing
2022
Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations
IEEE Access
Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
ArXiv, 2021
Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks
ArXiv, 2021