# Self Distillation via Iterative Constructive Perturbations

arXiv: https://arxiv.org/abs/2505.14751 · HTML: https://mlsanity.com/paper/2505.14751/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Multi-task Self-Supervised Visual Learning](https://mlsanity.com/paper/1708.07860/) (2017)
- [Self-Distillation Amplifies Regularization in Hilbert Space](https://mlsanity.com/paper/2002.05715/) (2020)
- [Regularizing Class-wise Predictions via Self-knowledge Distillation](https://mlsanity.com/paper/2003.13964/) (2020)
- [A Bayesian Perspective on Generalization and Stochastic Gradient Descent](https://mlsanity.com/paper/1710.06451/) (2017)
- [Snapshot Distillation: Teacher-Student Optimization in One Generation](https://mlsanity.com/paper/1812.00123/) (2018)
- [The AdEMAMix Optimizer: Better, Faster, Older](https://mlsanity.com/paper/2409.03137/) (2024)

## Abstract (arXiv)

Deep Neural Networks have achieved remarkable achievements across various domains, however balancing performance and generalization still remains a challenge while training these networks. In this paper, we propose a novel framework that uses a cyclic optimization strategy to concurrently optimize the model and its input data for better training, rethinking the traditional training paradigm. Central to our approach is Iterative Constructive Perturbation (ICP), which leverages the model's loss to iteratively perturb the input, progressively constructing an enhanced representation over some refinement steps. This ICP input is then fed back into the model to produce improved intermediate features, which serve as a target in a self-distillation framework against the original features. By alternately altering the model's parameters to the data and the data to the model, our method effectively addresses the gap between fitting and generalization, leading to enhanced performance. Extensive experiments demonstrate that our approach not only mitigates common performance bottlenecks in neural networks but also demonstrates significant improvements across training variations.