PinnedEdgeFace: Bringing Efficient Face Recognition to Edge DevicesFace recognition technology has made remarkable strides in recent years, primarily due to the advancements in deep neural networks and…Oct 11, 2024Oct 11, 2024
Training Multi-modal networks with Cross-Modal Focal LossHave you come across a scenario where you want to train a neural network with two or more modalities, and what happens one channel is…Nov 24, 2021Nov 24, 2021
One Class Contrastive Loss for Anomaly DetectionIn this tutorial, we will see howto use One Class Contrastive Loss (OCCL) for unseen attack detection, or for general anomaly detection.Feb 15, 20211Feb 15, 20211
Transfer Learning from Vision TransformersThe Transformers have been very popular in natural language processing (NLP) tasks. The recent paper An Image is Worth 16x16 Words…Nov 16, 20201Nov 16, 20201
Published inAnalytics VidhyaCan Your Face Detector Do Anti-spoofing?Typical face recognition systems can be fooled by attacks as simple as a printed photograph or by playing a video recording in front of…Jul 16, 2020Jul 16, 2020
Published inBecoming Human: Artificial Intelligence MagazineFace Presentation Attack Detection a.k.a Face AntispoofingWhat are presentation attacks?. How to detect them ?Apr 24, 2020Apr 24, 2020