Timezone: »

Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels
Songhua Wu · Xiaobo Xia · Tongliang Liu · Bo Han · Mingming Gong · Nannan Wang · Haifeng Liu · Gang Niu

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @

Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in \emph{pointwise} manners. Meanwhile, \emph{pairwise} manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner \emph{mitigate} label noise? To give an affirmative answer, in this paper, we propose a framework called \emph{Class2Simi}: it transforms data points with noisy \emph{class labels} to data pairs with noisy \emph{similarity labels}, where a similarity label denotes whether a pair shares the class label or not. Through this transformation, the \emph{reduction of the noise rate} is theoretically guaranteed, and hence it is in principle easier to handle noisy similarity labels. Amazingly, DNNs that predict the \emph{clean} class labels can be trained from noisy data pairs if they are first pretrained from noisy data points. Class2Simi is \emph{computationally efficient} because not only this transformation is on-the-fly in mini-batches, but also it just changes loss computation on top of model prediction into a pairwise manner. Its effectiveness is verified by extensive experiments.

Author Information

Songhua Wu (The University of Sydney)
Xiaobo Xia (The University of Sydney)
Tongliang Liu (The University of Sydney)
Mingming Gong (University of Melbourne)
Nannan Wang (Xidian University)
Haifeng Liu (Brain-Inspired Technology Co., Ltd.)
Gang Niu (RIKEN)
Gang Niu

Gang Niu is currently an indefinite-term senior research scientist at RIKEN Center for Advanced Intelligence Project.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors