# Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization

arXiv: https://arxiv.org/abs/2001.01578 · HTML: https://mlsanity.com/paper/2001.01578/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2020.

## Built on by (most cited first, 6 of 6)

- [Predicting the Susceptibility of Examples to Catastrophic Forgetting](https://mlsanity.com/paper/2406.09935/) (2024)
- [On robustness of generative representations against catastrophic forgetting](https://mlsanity.com/paper/2109.01844/) (2021)
- [Unified Regularity Measures for Sample-wise Learning and Generalization](https://mlsanity.com/paper/2108.03913/) (2021)
- [Overcoming Catastrophic Forgetting by XAI](https://mlsanity.com/paper/2211.14177/) (2022)
- [Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift](https://mlsanity.com/paper/2507.18653/) (2025)
- [Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models](https://mlsanity.com/paper/2602.02304/) (2026)

## Abstract (arXiv)

Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life. Taking the advancements from Explainable Artificial Intelligent, this paper proposes a novel technique called Auto DeepVis to dissect catastrophic forgetting in continual learning. A new method to deal with catastrophic forgetting named critical freezing is also introduced upon investigating the dilemma by Auto DeepVis. Experiments on a captioning model meticulously present how catastrophic forgetting happens, particularly showing which components are forgetting or changing. The effectiveness of our technique is then assessed; and more precisely, critical freezing claims the best performance on both previous and coming tasks over baselines, proving the capability of the investigation. Our techniques could not only be supplementary to existing solutions for completely eradicating catastrophic forgetting for life-long learning but also explainable.