# Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI

arXiv: https://arxiv.org/abs/2007.06712 · HTML: https://mlsanity.com/paper/2007.06712/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2020.

## Built on by (most cited first, 24 of 24)

- [Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching](https://mlsanity.com/paper/2311.17950/) (2023)
- [Exposing the Fake: Effective Diffusion-Generated Images Detection](https://mlsanity.com/paper/2307.06272/) (2023)
- [Elucidating the Design Space of Dataset Condensation](https://mlsanity.com/paper/2404.13733/) (2024)
- [Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again](https://mlsanity.com/paper/2210.04427/) (2022)
- [Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability](https://mlsanity.com/paper/2306.03715/) (2023)
- [TMI! Finetuned Models Leak Private Information from their Pretraining Data](https://mlsanity.com/paper/2306.01181/) (2023)
- [Class-Incremental Learning via Knowledge Amalgamation](https://mlsanity.com/paper/2209.02112/) (2022)
- [Energy-Latency Attacks: A New Adversarial Threat to Deep Learning](https://mlsanity.com/paper/2503.04963/) (2025)
- [EOOD: Entropy-based Out-of-distribution Detection](https://mlsanity.com/paper/2504.03342/) (2025)
- [Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch](https://mlsanity.com/paper/2405.13078/) (2024)
- [Towards Simple and Provable Parameter-Free Adaptive Gradient Methods](https://mlsanity.com/paper/2412.19444/) (2024)
- [Dynamic Rectification Knowledge Distillation](https://mlsanity.com/paper/2201.11319/) (2022)
- [Masked autoencoders are effective solution to transformer data-hungry](https://mlsanity.com/paper/2212.05677/) (2022)
- [Simple In-place Data Augmentation for Surveillance Object Detection](https://mlsanity.com/paper/2404.11226/) (2024)
- [Applications of Explainable artificial intelligence in Earth system science](https://mlsanity.com/paper/2406.11882/) (2024)
- [Energy Backdoor Attack to Deep Neural Networks](https://mlsanity.com/paper/2501.08152/) (2025)
- [An Efficient Sparse Fine-Tuning with Low Quantization Error via Neural Network Pruning](https://mlsanity.com/paper/2502.11439/) (2025)
- [Deep Transformers Thirst for Comprehensive-Frequency Data](https://mlsanity.com/paper/2203.07116/) (2022)
- [EXPRESSNET: An Explainable Residual Slim Network for Fingerprint Presentation Attack Detection](https://mlsanity.com/paper/2305.09397/) (2023)
- [CoViews: Adaptive Augmentation Using Cooperative Views for Enhanced Contrastive Learning](https://mlsanity.com/paper/2405.07116/) (2024)
- [Minimizing Energy Costs in Deep Learning Model Training: The Gaussian Sampling Approach](https://mlsanity.com/paper/2406.07332/) (2024)
- [Static IR Drop Prediction with Attention U-Net and Saliency-Based Explainability](https://mlsanity.com/paper/2408.03292/) (2024)
- [Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting](https://mlsanity.com/paper/2508.05059/) (2025)
- [NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning](https://mlsanity.com/paper/2608.04358/) (2026)

## Abstract (arXiv)

Understanding intermediate layers of a deep learning model and discovering the driving features of stimuli have attracted much interest, recently. Explainable artificial intelligence (XAI) provides a new way to open an AI black box and makes a transparent and interpretable decision. This paper proposes a new explainable convolutional neural network (XCNN) which represents important and driving visual features of stimuli in an end-to-end model architecture. This network employs encoder-decoder neural networks in a CNN architecture to represent regions of interest in an image based on its category. The proposed model is trained without localization labels and generates a heat-map as part of the network architecture without extra post-processing steps. The experimental results on the CIFAR-10, Tiny ImageNet, and MNIST datasets showed the success of our algorithm (XCNN) to make CNNs explainable. Based on visual assessment, the proposed model outperforms the current algorithms in class-specific feature representation and interpretable heatmap generation while providing a simple and flexible network architecture. The initial success of this approach warrants further study to enhance weakly supervised localization and semantic segmentation in explainable frameworks.