Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

locality-preserving CNN

A locality-preserving convolutional neural network is a deep learning model designed to learn discriminative feature representations by preserving the local neighborhood structure and geometric relationships of data in the feature space. Unlike standard networks that solely optimize for global class separation, this architecture incorporates locality-preserving loss objectives that pull locally proximate samples of the same class closer together while maximizing the distance between different classes. By maintaining the underlying manifold structure of the input data, it enhances the model capacity to handle complex visual patterns characterized by high intra-class diversity and subtle inter-class variations, making it particularly effective for challenging computer vision and recognition tasks.

1 item

Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild

Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild

Shan Li, Weihong Deng, Junping Du

OrganizationsBeijing University of Posts and Telecommunications

Why you should read this

Presents RAF-DB, a large-scale real-world facial expression database labeled through reliable crowdsourcing, alongside a deep locality-preserving CNN that significantly improves in-the-wild emotion recognition across basic and compound expressions.

Past research on facial expressions have used relatively limited datasets, which makes it unclear whether current methods can be employed in real world. In this paper, we present a novel database, RAF-DB, which contains about 30000 facial images from thousands of individuals. Each image has been individually labeled about 40 times, then EM algorithm was used to filter out unreliable labels. Crowdsourcing reveals that real-world faces often express compound emotions, or even mixture ones. For all we know, RAF-DB is the first database that contains compound expressions in the wild. Our cross-database study shows that the action units of basic emotions in RAF-DB are much more diverse than, or even deviate from, those of lab-controlled ones. To address this problem, we propose a new DLP-CNN (Deep Locality-Preserving CNN) method, which aims to enhance the discriminative power of deep features by preserving the locality closeness while maximizing the inter-class scatters. The benchmark experiments on the 7-class basic expressions and 11-class compound expressions, as well as the additional experiments on SFEW and CK+ databases, show that the proposed DLP-CNN outperforms the state-of-the-art handcrafted features and deep learning based methods for the expression recognition in the wild.

Added

2026-09-25