Photometric Transformer Networks and Label Adjustment for Breast Density Prediction

Jae-Hwan, Lee; Yoo, Donggeun; Kim, Hyo-Eun

doi:10.1109/iccvw.2019.00058

Cited by 13 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning from Noisy Labels: Neural network anti-noise training has made great progress. Current research are mainly focused on: estimating the noise transition matrix [7,[35][36][37][38][39][40], designing a robust loss function [41][42][43][44], correcting the noise label [45][46][47][48][49][50], sampling importance weighting [51][52][53][54][55] and meta-learning [56][57][58][59]. Our work is in the category of estimating the noise transition matrix.…”

Section: Related Workmentioning

confidence: 99%

Breaking the Dilemma of Medical Image-to-image Translation

Kong¹,

Lian²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Supervised Pix2Pix and unsupervised Cycle-consistency are two modes that dominate the field of medical image-to-image translation. However, neither modes are ideal. The Pix2Pix mode has excellent performance. But it requires paired and well pixel-wise aligned images, which may not always be achievable due to respiratory motion or anatomy change between times that paired images are acquired. The Cycle-consistency mode is less stringent with training data and works well on unpaired or misaligned images. But its performance may not be optimal. In order to break the dilemma of the existing modes, we propose a new unsupervised mode called RegGAN for medical image-to-image translation. It is based on the theory of "loss-correction". In RegGAN, the misaligned target images are considered as noisy labels and the generator is trained with an additional registration network to fit the misaligned noise distribution adaptively. The goal is to search for the common optimal solution to both image-to-image translation and registration tasks. We incorporated RegGAN into a few state-of-the-art image-to-image translation methods and demonstrated that RegGAN could be easily combined with these methods to improve their performances. Such as a simple CycleGAN in our mode surpasses latest NICEGAN even though using less network parameters. Based on our results, RegGAN outperformed both Pix2Pix on aligned data and Cycle-consistency on misaligned or unpaired data. RegGAN is insensitive to noises which makes it a better choice for a wide range of scenarios, especially for medical image-to-image translation tasks in which well pixel-wise aligned data are not available. Code and data used in this study can be found at https://github.com/Kid-Liet/Reg-GAN.

show abstract

Section: Related Workmentioning

confidence: 99%

Breaking the Dilemma of Medical Image-to-image Translation

Kong¹,

Lian²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Several methods have been proposed for the noisy-label problem, and they explore different strategies, such as robust loss functions (Wang et al, 2019a;, label cleansing (Jaehwan et al, 2019;Yuan et al, 2018), sample weighting (Ren et al, 2018), meta-learning (Han et al, 2018a), ensemble learning (Miao et al, 2015), and others (Yu et al, 2018;Kim et al, 2019;Zhang et al, 2019). Below, we focus on the prior work that is close to our approach and that show competitive results on the main benchmarks.…”

Section: Prior Workmentioning

confidence: 99%

LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment

Cordeiro¹,

Sachdeva²,

Belagiannis³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep neural network models are robust to a limited amount of label noise, but their ability to memorise noisy labels in high noise rate problems is still an open issue. The most competitive noisy-label learning algorithms rely on a 2-stage process comprising an unsupervised learning to classify training samples as clean or noisy, followed by a semi-supervised learning that minimises the empirical vicinal risk (EVR) using a labelled set formed by samples classified as clean, and an unlabelled set with samples classified as noisy. In this paper, we hypothesise that the generalisation of such 2-stage noisy-label learning methods depends on the precision of the unsupervised classifier and the size of the training set to minimise the EVR. We empirically validate these two hypotheses and propose the new 2stage noisy-label training algorithm LongReMix. We test LongReMix on the noisy-label benchmarks CIFAR-10, CIFAR-100, WebVision, Cloth-ing1M, and Food101-N. The results show that our LongReMix generalises better than competing approaches, particularly in high label noise problems. Furthermore, our approach achieves state-of-the-art performance in most datasets. The code will be available upon paper acceptance.

show abstract

“…Recently proposed noisy label learning methods rely on the following strategies: robust loss functions [36,49,51], sample selection [16], label cleansing [21,56], sample weighting [46], meta-learning [15], ensemble learning [38] and semi-supervised learning (SSL) [4]. The most successful approaches use SSL, combined with other methods [22,30,33].…”

Section: Prior Workmentioning

confidence: 99%

PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels

Cordeiro¹,

Belagiannis²,

Reid³

et al. 2021

Preprint

View full text Add to dashboard Cite

The most competitive noisy label learning methods rely on an unsupervised classification of clean and noisy samples, where samples classified as noisy are re-labelled and "MixMatched" with the clean samples. These methods have two issues in large noise rate problems: 1) the noisy set is more likely to contain hard samples that are incorrectly re-labelled, and 2) the number of samples produced by MixMatch tends to be reduced because it is constrained by the small clean set size. In this paper, we introduce the learning algorithm PropMix to handle the issues above. PropMix filters out hard noisy samples, with the goal of increasing the likelihood of correctly re-labelling the easy noisy samples. Also, PropMix places clean and re-labelled easy noisy samples in a training set that is augmented with MixUp, removing the clean set size constraint and including a large proportion of correctly re-labelled easy noisy samples. We also include self-supervised pre-training to improve robustness to high noisy label scenarios. Our experiments show that PropMix has state-of-the-art (SOTA) results on CIFAR-10/-100 (with symmetric, asymmetric and semantic label noise), Red Mini-ImageNet (from the Controlled Noisy Web Labels), Clothing1M and WebVision. In severe label noise benchmarks, our results are substantially better than other methods. The code is available at https://github.com/filipe-research/PropMix.

show abstract

Photometric Transformer Networks and Label Adjustment for Breast Density Prediction

Cited by 13 publications

References 11 publications

Breaking the Dilemma of Medical Image-to-image Translation

Breaking the Dilemma of Medical Image-to-image Translation

LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment

PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels

Contact Info

Product

Resources

About