# Robust Learning by Self-Transition for Handling Noisy Labels

arXiv: https://arxiv.org/abs/2012.04337 · HTML: https://mlsanity.com/paper/2012.04337/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 18 of 18)

- [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021)
- [Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization](https://mlsanity.com/paper/2308.06879/) (2023)
- [RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences](https://mlsanity.com/paper/2402.17257/) (2024)
- [Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries](https://mlsanity.com/paper/2203.15355/) (2022)
- [Early Stopping Against Label Noise Without Validation Data](https://mlsanity.com/paper/2502.07551/) (2025)
- [Instance-Dependent Noisy Label Learning via Graphical Modelling](https://mlsanity.com/paper/2209.00906/) (2022)
- [ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning](https://mlsanity.com/paper/2301.12077/) (2023)
- [Noisy Label Processing for Classification: A Survey](https://mlsanity.com/paper/2404.04159/) (2024)
- [A Survey of Dataset Refinement for Problems in Computer Vision Datasets](https://mlsanity.com/paper/2210.11717/) (2022)
- [Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples](https://mlsanity.com/paper/2502.08227/) (2025)
- [Diffusion on Graph: Augmentation of Graph Structure for Node Classification](https://mlsanity.com/paper/2503.12563/) (2025)
- [FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning](https://mlsanity.com/paper/2205.01310/) (2022)
- [Can LLMs Learn to Reason Robustly under Noisy Supervision?](https://mlsanity.com/paper/2604.03993/) (2026)
- [On Robust Learning from Noisy Labels: A Permutation Layer Approach](https://mlsanity.com/paper/2211.15890/) (2022)
- [Multi-Label Noise Transition Matrix Estimation with Label Correlations: Theory and Algorithm](https://mlsanity.com/paper/2309.12706/) (2023)
- [Sample selection with noise rate estimation in noise learning of medical image analysis](https://mlsanity.com/paper/2312.15233/) (2023)
- [MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images](https://mlsanity.com/paper/2505.18741/) (2025)
- [LogPurge: Log Data Purification for Anomaly Detection via Rule-Enhanced Filtering](https://mlsanity.com/paper/2511.14062/) (2025)

## Abstract (arXiv)

Real-world data inevitably contains noisy labels, which induce the poor generalization of deep neural networks. It is known that the network typically begins to rapidly memorize false-labeled samples after a certain point of training. Thus, to counter the label noise challenge, we propose a novel self-transitional learning method called MORPH, which automatically switches its learning phase at the transition point from seeding to evolution. In the seeding phase, the network is updated using all the samples to collect a seed of clean samples. Then, in the evolution phase, the network is updated using only the set of arguably clean samples, which precisely keeps expanding by the updated network. Thus, MORPH effectively avoids the overfitting to false-labeled samples throughout the entire training period. Extensive experiments using five real-world or synthetic benchmark datasets demonstrate substantial improvements over state-of-the-art methods in terms of robustness and efficiency.