Label Denoising with Large Ensembles of Heterogeneous Neural Networks

By Pavel Ostyakov, Elizaveta Logacheva, Roman Suvorov, Vladimir Aliev, Gleb Sterkin, Oleg Khomenko, Sergey I. Nikolenko. 2018

30 citations recorded by the source corpus.

Despite recent advances in computer vision based on various convolutional architectures, video understanding remains an important challenge. In this work, we present and discuss a top solution for the large-scale video classification (labeling) problem introduced as a Kaggle competition based on the YouTube-8M dataset. We show and compare different approaches to preprocessing, data augmentation, model architectures, and model combination. Our final model is based on a large ensemble of video- and frame-level models but fits into rather limiting hardware constraints. We apply an approach based on knowledge distillation to deal with noisy labels in the original dataset and the recently developed mixup technique to improve the basic models.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Continual Learning on Noisy Data Streams via Self-Purified Replay (2021, background): “There have been multiple lines of work to learn amidst noisy labels such as loss regularization [84, 96, 31], data re-weighting [68, 72], label cleaning [64, 42, 61], and”
Efficient Video Classification Using Fewer Frames (2019, methodology): “In the recently concluded competition (2018 version), many methods [24, 28, 30, 35, 8, 21, 31, 16] were proposed to compress the models such that they fit in 1GB of memory.”
A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images (2020, methodology): “Other techniques including consistency-based regularization [32], model ensemble [33] and iterative training [31] have also been used for learning from noisy labels for classiﬁcation.”
Deep learning with noisy labels: exploring techniques and remedies in medical image analysis (2019, methodology): “The same idea was successfully used in video classification by [70].”