Noise-Tolerant Paradigm for Training Face Recognition CNNs [Official, CVPR 2019]
Les fonctionnalités principales de huangyangyu/noiseface sont : Face Recognition, Robust Learning Frameworks.
Les alternatives open-source à huangyangyu/noiseface incluent : deepinsight/insightface — InsightFace is a comprehensive deep learning framework designed for face recognition, biometric identity verification,… alibaba-edu/ranking-based-instance-selection — Ranking-based-Instance-Selection. antoninbrthn/csidn — Code for the article "Confidence Scores Make Instance-dependent Label-noise Learning Possible", ICML'21. anuragkr90/webly-labeled-sounds — Github repo for webly labeled learning of sound events. arghosh/robustmw-net — WACV'21: Do We Really Need Gold Samples for Sample Weighting Under Label Noise? alfredxiangwu/lightcnn — A Light CNN for Deep Face Representation with Noisy Labels, TIFS 2018.
InsightFace is a comprehensive deep learning framework designed for face recognition, biometric identity verification, and feature extraction. It provides a specialized engine for one-to-one verification and one-to-many identification tasks, utilizing convolutional neural networks to transform raw image pixels into high-dimensional vector embeddings. The project includes a complete toolkit for detecting, aligning, and processing facial data to ensure consistent identity discrimination. Beyond core recognition, the platform distinguishes itself through an extensive model management and optimiz
Ranking-based-Instance-Selection
Code for the article "Confidence Scores Make Instance-dependent Label-noise Learning Possible", ICML'21
A Light CNN for Deep Face Representation with Noisy Labels, TIFS 2018