English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Noisy label Facial Expression Recognition (FER) is more challenging thantraditional noisy label classification tasks due to the inter-class similarityand the annotation ambiguity. Recent works mainly tackle this problem byfiltering out large-loss samples. In this paper, we explore dealing with noisylabels from a new feature-learning perspective. We find that FER modelsremember noisy samples by focusing on a part of the features that can beconsidered related to the noisy labels instead of learning from the wholefeatures that lead to the latent truth. Inspired by that, we propose a novelErasing Attention Consistency (EAC) method to suppress the noisy samples duringthe training process automatically. Specifically, we first utilize the flipsemantic consistency of facial images to design an imbalanced framework. Wethen randomly erase input images and use flip attention consistency to preventthe model from focusing on a part of the features. EAC significantlyoutperforms state-of-the-art noisy label FER methods and generalizes well toother tasks with a large number of classes like CIFAR100 and Tiny-ImageNet. Thecode is available athttps://github.com/zyh-uaiaaaa/Erasing-Attention-Consistency.

Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition