activity
20172024
most citedSample Selection with Uncertainty of Losses for Learning with Noisy Labels

49 citations · 114 across the 18 of their papers we have counts for

collaborators
Showing 2021Show all

7 papers · 1 filter

cs.CV2021

Unaligned Image-to-Image Translation by Learning to Reweight

Shaoan Xie, Mingming Gong, Yanwu Xu +1

Unsupervised image-to-image translation aims at learning the mapping from the source to target domain without using paired images for training. An essential yet restrictive assumpt…

cs.CV20211 cited

Box-Adapt: Domain-Adaptive Medical Image Segmentation using Bounding BoxSupervision

Yanwu Xu, Mingming Gong, Shaoan Xie +1

Deep learning has achieved remarkable success in medicalimage segmentation, but it usually requires a large numberof images labeled with fine-grained segmentation masks, andthe ann…

cs.CV2021

Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification

Pengfei Wang, Changxing Ding, Wentao Tan +3

Unsupervised Domain Adaptive (UDA) object re-identification (Re-ID) aims at adapting a model trained on a labeled source domain to an unlabeled target domain. State-of-the-art obje…

cs.LG2021

Kernel Mean Estimation by Marginalized Corrupted Distributions

Xiaobo Xia, Shuo Shan, Mingming Gong +4

Estimating the kernel mean in a reproducing kernel Hilbert space is a critical component in many kernel learning algorithms. Given a finite sample, the standard estimate of the tar…

cs.LG20217 cited

Instance Correction for Learning with Open-set Noisy Labels

Xiaobo Xia, Tongliang Liu, Bo Han +4

The problem of open-set noisy labels denotes that part of training data have a different label space that does not contain the true class. Lots of approaches, e.g., loss correction…

cs.LG202149 cited

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

Xiaobo Xia, Tongliang Liu, Bo Han +4

In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-t…