Robust Learning by Self-Transition for Handling Noisy Labels
By Hwanjun Song, Minseok Kim, Dongmin Park, Yooju Shin, Jae-Gil Lee. 2020
46 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Civil and Structural Engineering, Industrial and Manufacturing Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Hyun-woo Koh
- Yuji Roh
- Jonghyun Choi
- Steven Euijong Whang
- Jung-Woo Ha
- Seulki Park
- Jae-Gil Lee
- Hwanjun Song
Citations in the corpus
- Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries (2022, background): “In modern approaches of handling noisy labels [14, 33, 38], only the clean set is used to train the model in a supervised manner, while the noisy set is discarded for robust learning.”
- Data collection and quality challenges in deep learning: a data-centric AI perspective (2021, background): “MORPH [152] further improves Prestopping through a novel concept of self-transitional learning , which automatically switches its learning phase at the transition point.”