Log In Sign Up

Co-Seg: An Image Segmentation Framework Against Label Corruption

by   Ziyi Huang, et al.

Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly trained on noisy datasets, leading to severe performance degradation at test time. In this paper, we propose a novel deep learning framework, namely Co-Seg, to collaboratively train segmentation networks on datasets which include low-quality noisy labels. Our approach first trains two networks simultaneously to sift through all samples and obtain a subset with reliable labels. Then, an efficient yet easily-implemented label correction strategy is applied to enrich the reliable subset. Finally, using the updated dataset, we retrain the segmentation network to finalize its parameters. Experiments in two noisy labels scenarios demonstrate that our proposed model can achieve results comparable to those obtained from supervised learning trained on the noise-free labels. In addition, our framework can be easily implemented in any segmentation algorithm to increase its robustness to noisy labels.


page 1

page 2

page 3

page 4


KNN-enhanced Deep Learning Against Noisy Labels

Supervised learning on Deep Neural Networks (DNNs) is data hungry. Optim...

Deep Learning is Robust to Massive Label Noise

Deep neural networks trained on large supervised datasets have led to im...

Cross-denoising Network against Corrupted Labels in Medical Image Segmentation with Domain Shift

Deep convolutional neural networks (DCNNs) have contributed many breakth...

Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation

Manually segmenting the hepatic vessels from Computer Tomography (CT) is...

Co-matching: Combating Noisy Labels by Augmentation Anchoring

Deep learning with noisy labels is challenging as deep neural networks h...

Co-sampling: Training Robust Networks for Extremely Noisy Supervision

Training robust deep networks is challenging under noisy labels. Current...

ExpertNet: Adversarial Learning and Recovery Against Noisy Labels

Today's available datasets in the wild, e.g., from social media and open...